diff --git a/docs/source/examples.rst b/docs/source/examples.rst
index 517f1b6..a3ef41e 100644
--- a/docs/source/examples.rst
+++ b/docs/source/examples.rst
@@ -31,9 +31,9 @@ When reading this script, note the basic workflow. After the data is loaded, a m
 
 Next, the model is moved to the GPU using the :code:`model.to` function. Any device understood by :code:`torch.Tensor.to` can be specified here. The next line is a bit more subtle - the dataset is told to move patterns to the GPU before passing them to the model using the :code:`dataset.get_as` function. This function does not move the stored patterns to the GPU. If there is sufficient GPU memory, the patterns can also be pre-moved to the GPU using :code:`dataset.to`, but the speedup is empirically quite small.
 
-Once the device is selected, a reconstruction is run using :code:`model.Adam_optimize`. This is a generator function which will yield at every epoch, to allow some monitoring code to be run.
+Once the device is selected, a reconstruction is run using :code:`model.Adam_optimize`. This is a generator function which will yield at the end of every epoch, to allow some monitoring code to be run.
 
-Finally, the results can be studied using :code:`model.inspect(dataet)`, which creates or updates a set of plots showing the current state of the model parameters. :code:`model.compare(dataset)` is also called, which shows how the simulated diffraction patterns compare to the measured diffraction patterns in the dataset.
+Finally, the results can be studied using :code:`model.inspect(dataset)`, which creates or updates a set of plots showing the current state of the model parameters. :code:`model.compare(dataset)` is also called, which shows how the simulated diffraction patterns compare to the measured diffraction patterns in the dataset.
 
 
 Fancy Ptycho
@@ -63,6 +63,12 @@ By default, FancyPtycho will also optimize over the following model parameters,
 
 These corrections can be turned off (on) by calling :code:`model.<parameter>.requires_grad = False #(True)`.
 
+Note as well two other changes that are made in this script, when compared to `simple_ptycho.py`. First, a `Reconstructor` object is explicitly created, in this case an `AdamReconstructor`. This object stores a model, dataset, and pytorch optimizer. It is then used to orchestrate the later reconstruction using a call to `Reconstructor.optimize()`.
+
+We use this pattern, instead of the simpler call to `model.Adam_optimize()`, because having the reconstructor store the optimizer as well as the model and dataset allows the moment estimates to persist between multiple rounds of optimization. This leads to the second change: In this script, we run two optimization loops. The first loop aggressively refines the probe, with a low minibatch size and a high learning rate. The second loop has a smaller learning rate and a larger batch size, which allow for a more precise final estimation of the object.
+
+In this case, we used one reconstructor, but it is possible to create additional reconstructors to zero out all the persistant information in the optimizer, if desired, or even to instantiate multiple reconstructors on the same model with different optimization algorithms (e.g. `model.LBFGS_optimize()`).
+
 
 Gold Ball Ptycho
 ----------------
diff --git a/docs/source/index.rst b/docs/source/index.rst
index c6fcb8d..b8cd288 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -9,6 +9,7 @@
    general
    datasets
    models
+   reconstructors
    tools/index
    indices_tables
    
diff --git a/docs/source/reconstructors.rst b/docs/source/reconstructors.rst
new file mode 100644
index 0000000..2e78a74
--- /dev/null
+++ b/docs/source/reconstructors.rst
@@ -0,0 +1,5 @@
+Reconstructors
+==============
+
+.. automodule:: cdtools.reconstructors
+   :members:
diff --git a/examples/fancy_ptycho.py b/examples/fancy_ptycho.py
index 1cf5855..ebee68f 100644
--- a/examples/fancy_ptycho.py
+++ b/examples/fancy_ptycho.py
@@ -19,19 +19,27 @@ device = 'cuda'
 model.to(device=device)
 dataset.get_as(device=device)
 
+# For this script, we use a slightly different pattern where we explicitly
+# create a `Reconstructor` class to orchestrate the reconstruction. The
+# reconstructor will store the model and dataset and create an appropriate
+# optimizer. This allows the optimizer to persist between loops, along with
+# e.g. estimates of the moments of individual parameters
+recon = cdtools.reconstructors.AdamReconstructor(model, dataset)
+
 # The learning rate parameter sets the alpha for Adam.
 # The beta parameters are (0.9, 0.999) by default
 # The batch size sets the minibatch size
-for loss in model.Adam_optimize(50, dataset, lr=0.02, batch_size=10):
+for loss in recon.optimize(50, lr=0.02, batch_size=10):
     print(model.report())
     # Plotting is expensive, so we only do it every tenth epoch
     if model.epoch % 10 == 0:
         model.inspect(dataset)
 
 # It's common to chain several different reconstruction loops. Here, we
-# started with an aggressive refinement to find the probe, and now we
-# polish the reconstruction with a lower learning rate and larger minibatch
-for loss in model.Adam_optimize(50, dataset,  lr=0.005, batch_size=50):
+# started with an aggressive refinement to find the probe in the previous
+# loop, and now we polish the reconstruction with a lower learning rate
+# and larger minibatch
+for loss in recon.optimize(50, lr=0.005, batch_size=50):
     print(model.report())
     if model.epoch % 10 == 0:
         model.inspect(dataset)
diff --git a/examples/gold_ball_ptycho.py b/examples/gold_ball_ptycho.py
index 4747666..4971975 100644
--- a/examples/gold_ball_ptycho.py
+++ b/examples/gold_ball_ptycho.py
@@ -29,6 +29,7 @@ model = cdtools.models.FancyPtycho.from_dataset(
     probe_fourier_crop=pad 
 )
 
+
 # This is a trick that my grandmother taught me, to combat the raster grid
 # pathology: we randomze the our initial guess of the probe positions.
 # The units here are pixels in the object array.
@@ -42,17 +43,20 @@ device = 'cuda'
 model.to(device=device)
 dataset.get_as(device=device)
 
+# Create the reconstructor
+recon = cdtools.reconstructors.AdamReconstructor(model, dataset)
+
 # This will save out the intermediate results if an exception is thrown
 # during the reconstruction
 with model.save_on_exception(
         'example_reconstructions/gold_balls_earlyexit.h5', dataset):
     
-    for loss in model.Adam_optimize(20, dataset, lr=0.005, batch_size=50):
+    for loss in recon.optimize(20, lr=0.005, batch_size=50):
         print(model.report())
         if model.epoch % 10 == 0:
             model.inspect(dataset)
 
-    for loss in model.Adam_optimize(50, dataset, lr=0.002, batch_size=100):
+    for loss in recon.optimize(50, lr=0.002, batch_size=100):
         print(model.report())
         if model.epoch % 10 == 0:
             model.inspect(dataset)
@@ -64,8 +68,7 @@ with model.save_on_exception(
 
     # Setting schedule=True automatically lowers the learning rate if
     # the loss fails to improve after 10 epochs
-    for loss in model.Adam_optimize(100, dataset, lr=0.001, batch_size=100,
-                                    schedule=True):
+    for loss in recon.optimize(100, lr=0.001, batch_size=100, schedule=True):
         print(model.report())
         if model.epoch % 10 == 0:
             model.inspect(dataset)
diff --git a/examples/gold_ball_split.py b/examples/gold_ball_split.py
index 8624b9f..9fc5b08 100644
--- a/examples/gold_ball_split.py
+++ b/examples/gold_ball_split.py
@@ -36,15 +36,18 @@ for label, dataset in zip(labels, datasets):
     model.to(device=device)
     dataset.get_as(device=device)
 
+    # Create the reconstructor
+    recon = cdtools.reconstructors.AdamReconstructor(model, dataset)
+
     # For batched reconstructions like this, there's no need to live-plot
     # the progress
-    for loss in model.Adam_optimize(20, dataset, lr=0.005, batch_size=50):
+    for loss in recon.optimize(20, lr=0.005, batch_size=50):
         print(model.report())
 
-    for loss in model.Adam_optimize(50, dataset, lr=0.002, batch_size=100):
+    for loss in recon.optimize(50, lr=0.002, batch_size=100):
         print(model.report())
 
-    for loss in model.Adam_optimize(100, dataset, lr=0.001, batch_size=100,
+    for loss in recon.optimize(100, lr=0.001, batch_size=100,
                                     schedule=True):
         print(model.report())
 
diff --git a/examples/simple_ptycho.py b/examples/simple_ptycho.py
index 726af94..217d96b 100644
--- a/examples/simple_ptycho.py
+++ b/examples/simple_ptycho.py
@@ -1,3 +1,12 @@
+"""
+Runs a very simple reconstruction using the SimplePtycho model, which was
+designed to be an easy introduction to show how the models are made and used.
+
+For a more realistic example of how to use cdtools for real-world data,
+look at fancy_ptycho.py and gold_ball_ptycho.py, both of which use the
+more powerful FancyPtycho model and include more information on how to
+correct for common sources of error.
+"""
 import cdtools
 from matplotlib import pyplot as plt
 
@@ -13,7 +22,7 @@ device = 'cuda'
 model.to(device=device)
 dataset.get_as(device=device)
 
-# We run the actual reconstruction
+# We run the reconstruction
 for loss in model.Adam_optimize(100, dataset, batch_size=10):
     # We print a quick report of the optimization status
     print(model.report())
diff --git a/src/cdtools/models/base.py b/src/cdtools/models/base.py
index 635cdfb..df347b6 100644
--- a/src/cdtools/models/base.py
+++ b/src/cdtools/models/base.py
@@ -40,6 +40,7 @@ import time
 from scipy import io
 from contextlib import contextmanager
 from cdtools.tools.data import nested_dict_to_h5, h5_to_nested_dict, nested_dict_to_numpy, nested_dict_to_torch
+from cdtools.reconstructors import AdamReconstructor, LBFGSReconstructor, SGDReconstructor
 from cdtools.datasets import CDataset
 from typing import List, Union, Tuple
 import os
@@ -374,31 +375,24 @@ class CDIModel(t.nn.Module):
             only the calculation speed. 
         
         """
-        # We want to have model.Adam_optimize call AND store
-        # cdtools.reconstructors.AdamReconstructor to perform reconstructions
-        # without creating a new reconstructor each time we update the
-        # hyperparameters.
-        #
-        # The only way to do this is to make the Adam reconstructor an
-        # attribute of the model. But since the Adam reconstructor also
-        # depends on CDIModel, this seems to give rise to a circular import
-        # error unless we import cdtools.reconstructors within this method:
-        if not hasattr(self, 'reconstructor'):
-            from cdtools.reconstructors import AdamReconstructor
-            self.reconstructor = AdamReconstructor(model=self,
-                                                   dataset=dataset,
-                                                   subset=subset)
+        reconstructor = AdamReconstructor(
+            model=self,
+            dataset=dataset,
+            subset=subset,
+        )
         
         # Run some reconstructions
-        return self.reconstructor.optimize(iterations=iterations,
-                                           batch_size=batch_size,
-                                           lr=lr,
-                                           betas=betas,
-                                           schedule=schedule,
-                                           amsgrad=amsgrad,
-                                           regularization_factor=regularization_factor, # noqa
-                                           thread=thread,
-                                           calculation_width=calculation_width)
+        return reconstructor.optimize(
+            iterations=iterations,
+            batch_size=batch_size,
+            lr=lr,
+            betas=betas,
+            schedule=schedule,
+            amsgrad=amsgrad,
+            regularization_factor=regularization_factor, # noqa
+            thread=thread,
+            calculation_width=calculation_width,
+        )
 
     def LBFGS_optimize(self,
                        iterations: int,
@@ -445,29 +439,23 @@ class CDIModel(t.nn.Module):
             round of gradient accumulation. Does not affect the result, only
             the calculation speed.
         """
-        # We want to have model.LBFGS_optimize store
-        # cdtools.reconstructors.LBFGSReconstructor as an attribute to run
-        # reconstructions without generating new reconstructors each time
-        # CDIModel.LBFGS_optimize is called.
-        #
-        # Since the LBFGS reconstructor also depends on CDIModel, a circular
-        # import error arises unless we import cdtools.reconstructors within
-        # this method:
-        if not hasattr(self, 'reconstructor'):
-            from cdtools.reconstructors import LBFGSReconstructor
-            self.reconstructor = LBFGSReconstructor(model=self,
-                                                    dataset=dataset,
-                                                    subset=subset)
+        reconstructor = LBFGSReconstructor(
+            model=self,
+            dataset=dataset,
+            subset=subset,
+        )
         
         # Run some reconstructions
-        return self.reconstructor.optimize(iterations=iterations,
-                                           lr=lr,
-                                           history_size=history_size,
-                                           regularization_factor=regularization_factor, # noqa
-                                           thread=thread,
-                                           calculation_width=calculation_width,
-                                           line_search_fn=line_search_fn)
-
+        return reconstructor.optimize(
+            iterations=iterations,
+            lr=lr,
+            history_size=history_size,
+            regularization_factor=regularization_factor, # noqa
+            thread=thread,
+            calculation_width=calculation_width,
+            line_search_fn=line_search_fn,
+        )
+    
     def SGD_optimize(self, 
                      iterations: int,
                      dataset: CDataset,
@@ -520,31 +508,25 @@ class CDIModel(t.nn.Module):
             round of gradient accumulation.
 
         """
-        # We want to have model.SGD_optimize store
-        # cdtools.reconstructors.SGDReconstructor as an attribute to run
-        # reconstructions without generating new reconstructors each time
-        # CDIModel.SGD_optimize is called.
-        #
-        # Since the SGD reconstructor also depends on CDIModel, a circular
-        # import error arises unless we import cdtools.reconstructors within
-        # this method:
-        if not hasattr(self, 'reconstructor'):
-            from cdtools.reconstructors import SGDReconstructor
-            self.reconstructor = SGDReconstructor(model=self, 
-                                                  dataset=dataset, 
-                                                  subset=subset)
+        reconstructor = SGDReconstructor(
+            model=self, 
+            dataset=dataset, 
+            subset=subset,
+        )
 
         # Run some reconstructions
-        return self.reconstructor.optimize(iterations=iterations,
-                                           batch_size=batch_size,
-                                           lr=lr,
-                                           momentum=momentum,
-                                           dampening=dampening,
-                                           weight_decay=weight_decay,
-                                           nesterov=nesterov,
-                                           regularization_factor=regularization_factor, # noqa
-                                           thread=thread,
-                                           calculation_width=calculation_width)
+        return reconstructor.optimize(
+            iterations=iterations,
+            batch_size=batch_size,
+            lr=lr,
+            momentum=momentum,
+            dampening=dampening,
+            weight_decay=weight_decay,
+            nesterov=nesterov,
+            regularization_factor=regularization_factor, # noqa
+            thread=thread,
+            calculation_width=calculation_width,
+        )
 
 
     def report(self):
diff --git a/src/cdtools/reconstructors/adam.py b/src/cdtools/reconstructors/adam.py
index 6eecc9c..e298bdb 100644
--- a/src/cdtools/reconstructors/adam.py
+++ b/src/cdtools/reconstructors/adam.py
@@ -6,12 +6,17 @@ The Reconstructor class is designed to resemble so-called
 'Trainer' classes that (in the language of the AI/ML folks) handles
 the 'training' of a model given some dataset and optimizer.
 """
+from __future__ import annotations
+from typing import TYPE_CHECKING
+
 import torch as t
-from cdtools.datasets.ptycho_2d_dataset import Ptycho2DDataset
-from cdtools.models import CDIModel
 from typing import Tuple, List, Union
 from cdtools.reconstructors import Reconstructor
 
+if TYPE_CHECKING:
+    from cdtools.models import CDIModel
+    from cdtools.datasets.ptycho_2d_dataset import Ptycho2DDataset
+
 __all__ = ['AdamReconstructor']
 
 
@@ -46,10 +51,12 @@ class AdamReconstructor(Reconstructor):
                  dataset: Ptycho2DDataset,
                  subset: List[int] = None):
 
-        super().__init__(model, dataset, subset)
-
         # Define the optimizer for use in this subclass
-        self.optimizer = t.optim.Adam(self.model.parameters())
+        optimizer = t.optim.Adam(model.parameters())
+
+        super().__init__(model, dataset, optimizer, subset=subset)
+
+
 
     def adjust_optimizer(self,
                          lr: int = 0.005,
@@ -74,11 +81,13 @@ class AdamReconstructor(Reconstructor):
             param_group['betas'] = betas
             param_group['amsgrad'] = amsgrad
 
+        
     def optimize(self,
                  iterations: int,
                  batch_size: int = 15,
                  lr: float = 0.005,
                  betas: Tuple[float] = (0.9, 0.999),
+                 custom_data_loader: t.utils.data.DataLoader = None,
                  schedule: bool = False,
                  amsgrad: bool = False,
                  regularization_factor: Union[float, List[float]] = None,
@@ -94,6 +103,12 @@ class AdamReconstructor(Reconstructor):
         (formerly `CDIModel.AD_optimize`) to run a round of reconstruction
         once the dataloader and optimizer hyperparameters have been
         set up.
+        
+        The `batch_size` parameter sets the batch size for the default
+        dataloader. If a custom data loader is desired, it can be passed
+        in to the `custom_data_loader` argument, which will override the
+        `batch_size` and `shuffle` parameters
+
 
         Parameters
         ----------
@@ -110,6 +125,9 @@ class AdamReconstructor(Reconstructor):
         schedule : bool
             Optional, create a learning rate scheduler
             (torch.optim.lr_scheduler._LRScheduler).
+        custom_data_loader : t.utils.data.DataLoader
+            Optional, a custom DataLoader to use. If set, will override
+            batch_size.
         amsgrad : bool
             Optional, whether to use the AMSGrad variant of this algorithm.
         regularization_factor : float or list(float)
@@ -133,18 +151,13 @@ class AdamReconstructor(Reconstructor):
             f'{regularization_factor}, and schedule = {schedule}.\n'
         )
 
-        # 1) The subset statement is contained in Reconstructor.__init__
-
-        # 2) Set up / re-initialize the data laoder
-        self.setup_dataloader(batch_size=batch_size, shuffle=shuffle)
-
-        # 3) The optimizer is created in self.__init__, but the
-        #    hyperparameters need to be set up with self.adjust_optimizer
+        # The optimizer is created in self.__init__, but the
+        # hyperparameters need to be set up with self.adjust_optimizer
         self.adjust_optimizer(lr=lr,
                               betas=betas,
                               amsgrad=amsgrad)
 
-        # 4) Set up the scheduler
+        # Set up the scheduler
         if schedule:
             self.scheduler = \
                 t.optim.lr_scheduler.ReduceLROnPlateau(self.optimizer,
@@ -153,8 +166,13 @@ class AdamReconstructor(Reconstructor):
         else:
             self.scheduler = None
 
-        # 5) This is analagous to making a call to CDIModel.AD_optimize
-        return super(AdamReconstructor, self).optimize(iterations,
-                                                       regularization_factor,
-                                                       thread,
-                                                       calculation_width)
+        # Now, we run the optimize routine defined in the base class
+        return super(AdamReconstructor, self).optimize(
+            iterations,
+            batch_size=batch_size,
+            custom_data_loader=custom_data_loader,
+            regularization_factor=regularization_factor,
+            thread=thread,
+            calculation_width=calculation_width,
+            shuffle=shuffle,
+        )
diff --git a/src/cdtools/reconstructors/base.py b/src/cdtools/reconstructors/base.py
index fd2cbb2..cf3de8c 100644
--- a/src/cdtools/reconstructors/base.py
+++ b/src/cdtools/reconstructors/base.py
@@ -8,16 +8,21 @@ the 'training' of a model given some dataset and optimizer.
 The subclasses of Reconstructor are required to implement
 their own data loaders and optimizer adjusters
 """
+from __future__ import annotations
+from typing import TYPE_CHECKING
 
 import torch as t
 from torch.utils import data as td
 import threading
 import queue
 import time
-from cdtools.datasets import CDataset
-from cdtools.models import CDIModel
 from typing import List, Union
 
+if TYPE_CHECKING:
+    from cdtools.models import CDIModel
+    from cdtools.datasets import CDataset
+    
+
 __all__ = ['Reconstructor']
 
 
@@ -35,46 +40,51 @@ class Reconstructor:
         Model for CDI/ptychography reconstruction
     dataset: CDataset
         The dataset to reconstruct against
+    optimizer: torch.optim.Optimizer
+        The optimizer to use for the reconstruction
     subset : list(int) or int
         Optional, a pattern index or list of pattern indices to use
 
-    Important attributes:
-    - **model** -- Always points to the core model used.
-    - **optimizer** -- A `torch.optim.Optimizer` that must be defined when
-        initializing the Reconstructor subclass.
-    - **scheduler** -- A `torch.optim.lr_scheduler` that may be defined during
-        the `optimize` method.
-    - **data_loader** -- A torch.utils.data.DataLoader that is defined by
-        calling the `setup_dataloader` method.
+    Attributes
+    ----------
+    model : CDIModel
+        Points to the core model used.
+    optimizer : torch.optim.Optimizer
+        Must be defined when initializing the Reconstructor subclass.
+    scheduler : torch.optim.lr_scheduler, optional
+        May be defined during the ``optimize`` method.
+    data_loader : torch.utils.data.DataLoader
+        Defined by calling the ``setup_dataloader`` method.
     """
     def __init__(self,
                  model: CDIModel,
                  dataset: CDataset,
+                 optimizer: t.optim.Optimizer,
                  subset: Union[int, List[int]] = None):
+        
         # Store parameters as attributes of Reconstructor
-        self.subset = subset
-
-        # Initialize attributes that must be defined by the subclasses
-        self.optimizer = None
-        self.scheduler = None
-        self.data_loader = None
-
-        # Store the original model
         self.model = model
+        self.optimizer = optimizer
 
-        # Store the dataset
+        # Store the dataset, clipping it to a subset if needed
         if subset is not None:
             # if subset is just one pattern, turn into a list for convenience
             if isinstance(subset, int):
                 subset = [subset]
             dataset = td.Subset(dataset, subset)
+
         self.dataset = dataset
 
+        # Initialize attributes that must be defined by the subclasses
+        self.scheduler = None
+        self.data_loader = None
+
+
     def setup_dataloader(self,
                          batch_size: int = None,
                          shuffle: bool = True):
         """
-        Sets up / re-initializes the dataloader.
+        Sets up or re-initializes the dataloader.
 
         Parameters
         ----------
@@ -91,6 +101,7 @@ class Reconstructor:
         else:
             self.data_loader = td.Dataloader(self.dataset)
 
+            
     def adjust_optimizer(self, **kwargs):
         """
         Change hyperparameters for the utilized optimizer.
@@ -100,7 +111,8 @@ class Reconstructor:
         """
         raise NotImplementedError()
 
-    def _run_epoch(self,
+    
+    def run_epoch(self,
                    stop_event: threading.Event = None,
                    regularization_factor: Union[float, List[float]] = None,
                    calculation_width: int = 10):
@@ -128,6 +140,18 @@ class Reconstructor:
             diffraction pattern intensity
         """
 
+        # Setting this as an explicit catch makes me feel more comfortable
+        # exposing it as a public method. This way a user won't be confused
+        # if they try to use this directly
+        if self.data_loader is None:
+            raise RuntimeError(
+                'No data loader was defined. Please run '
+                'Reconstructor.setup_dataloader() before running '
+                'Reconstructor.run_epoch(), or use Reconstructor.optimize(), '
+                'which does it automatically.'
+            )
+        
+        
         # Initialize some tracking variables
         normalization = 0
         loss = 0
@@ -207,9 +231,12 @@ class Reconstructor:
 
     def optimize(self,
                  iterations: int,
+                 batch_size: int = 1,
+                 custom_data_loader: torch.utils.data.DataLoader = None,
                  regularization_factor: Union[float, List[float]] = None,
                  thread: bool = True,
-                 calculation_width: int = 10):
+                 calculation_width: int = 10,
+                 shuffle=True):
         """
         Runs a round of reconstruction using the provided optimizer
 
@@ -228,10 +255,25 @@ class Reconstructor:
         the plots. This behavior can be turned off by setting the keyword
         argument 'thread' to False.
 
+        The `batch_size` parameter sets the batch size for the default
+        dataloader. If a custom data loader is desired, it can be passed
+        in to the `custom_data_loader` argument, which will override the
+        `batch_size` and `shuffle` parameters
+
+        Please see `AdamReconstructor.optimize()` for an example of how to
+        override this function when designing a subclass
+
         Parameters
         ----------
         iterations : int
             How many epochs of the algorithm to run.
+        batch_size : int
+            Optional, the batch size to use. Default is 1. This is typically
+            overridden by subclasses with an appropriate default for the
+            specific optimizer.
+        custom_data_loader : torch.utils.data.DataLoader
+            Optional, a custom DataLoader to use. Will override batch_size
+            if set.
         regularization_factor : float or list(float)
             Optional, if the model has a regularizer defined, the set of
             parameters to pass the regularizer method.
@@ -242,6 +284,10 @@ class Reconstructor:
             Default 10, how many translations to pass through at once for each
             round of gradient accumulation. This does not affect the result,
             but may affect the calculation speed.
+        shuffle : bool
+            Optional, enable/disable shuffling of the dataset. This option
+            is intended for diagnostic purposes and should be left as True.
+
 
         Yields
         ------
@@ -250,6 +296,11 @@ class Reconstructor:
             diffraction pattern intensity.
         """
 
+        if custom_data_loader is None:
+            self.setup_dataloader(batch_size=batch_size, shuffle=shuffle)
+        else:
+            self.data_loader = custom_data_loader
+
         # We store the current optimizer as a model parameter so that
         # it can be saved and loaded for checkpointing
         self.current_optimizer = self.optimizer
@@ -265,8 +316,10 @@ class Reconstructor:
                         yield float('nan')
                     continue
 
-                yield self._run_epoch(regularization_factor=regularization_factor, # noqa
-                                      calculation_width=calculation_width)
+                yield self.run_epoch(
+                    regularization_factor=regularization_factor, # noqa
+                    calculation_width=calculation_width,
+                )
 
         # But if we do want to thread, it's annoying:
         else:
@@ -277,9 +330,12 @@ class Reconstructor:
             def target():
                 try:
                     result_queue.put(
-                        self._run_epoch(stop_event=stop_event,
-                                        regularization_factor=regularization_factor, # noqa
-                                        calculation_width=calculation_width))
+                        self.run_epoch(
+                            stop_event=stop_event,
+                            regularization_factor=regularization_factor, # noqa
+                            calculation_width=calculation_width,
+                        )
+                    )
                 except Exception as e:
                     # If something bad happens, put the exception into the
                     # result queue
diff --git a/src/cdtools/reconstructors/lbfgs.py b/src/cdtools/reconstructors/lbfgs.py
index 8bbd7ae..8907782 100644
--- a/src/cdtools/reconstructors/lbfgs.py
+++ b/src/cdtools/reconstructors/lbfgs.py
@@ -6,12 +6,18 @@ The Reconstructor class is designed to resemble so-called
 'Trainer' classes that (in the language of the AI/ML folks) handles
 the 'training' of a model given some dataset and optimizer.
 """
+from __future__ import annotations
+from typing import TYPE_CHECKING
+
 import torch as t
-from cdtools.datasets.ptycho_2d_dataset import Ptycho2DDataset
-from cdtools.models import CDIModel
 from typing import List, Union
 from cdtools.reconstructors import Reconstructor
 
+if TYPE_CHECKING:
+    from cdtools.models import CDIModel
+    from cdtools.datasets.ptycho_2d_dataset import Ptycho2DDataset
+
+
 __all__ = ['LBFGSReconstructor']
 
 
@@ -47,10 +53,16 @@ class LBFGSReconstructor(Reconstructor):
                  dataset: Ptycho2DDataset,
                  subset: List[int] = None):
 
-        super().__init__(model, dataset, subset)
-
         # Define the optimizer for use in this subclass
-        self.optimizer = t.optim.LBFGS(self.model.parameters())
+        optimizer = t.optim.LBFGS(model.parameters())
+        
+        super().__init__(
+            model,
+            dataset,
+            optimizer,
+            subset=subset,
+        )
+
 
     def adjust_optimizer(self,
                          lr: int = 0.005,
@@ -115,20 +127,17 @@ class LBFGSReconstructor(Reconstructor):
             round of gradient accumulation. Does not affect the result, only
             the calculation speed.
         """
-        # 1) The subset statement is contained in Reconstructor.__init__
 
-        # 2) Set up / re-initialize the data loader. For LBFGS, we load
-        #    all the data at once.
-        self.setup_dataloader(batch_size=len(self.dataset))
-
-        # 3) The optimizer is created in self.__init__, but the
-        #    hyperparameters need to be set up with self.adjust_optimizer
+        # The optimizer is created in self.__init__, but the
+        # hyperparameters need to be set up with self.adjust_optimizer
         self.adjust_optimizer(lr=lr,
                               history_size=history_size,
                               line_search_fn=line_search_fn)
 
-        # 4) This is analagous to making a call to CDIModel.AD_optimize
-        return super(LBFGSReconstructor, self).optimize(iterations,
-                                                        regularization_factor,
-                                                        thread,
-                                                        calculation_width)
+        # Now, we run the optimize routine defined in the base class
+        return super(LBFGSReconstructor, self).optimize(
+            iterations,
+            batch_size=len(self.dataset),
+            regularization_factor=regularization_factor,
+            thread=thread,
+            calculation_width=calculation_width)
diff --git a/src/cdtools/reconstructors/sgd.py b/src/cdtools/reconstructors/sgd.py
index a8f2ebc..cb1e26b 100644
--- a/src/cdtools/reconstructors/sgd.py
+++ b/src/cdtools/reconstructors/sgd.py
@@ -6,12 +6,18 @@ The Reconstructor class is designed to resemble so-called
 'Trainer' classes that (in the language of the AI/ML folks) handles
 the 'training' of a model given some dataset and optimizer.
 """
+from __future__ import annotations
+from typing import TYPE_CHECKING
+
 import torch as t
-from cdtools.datasets.ptycho_2d_dataset import Ptycho2DDataset
-from cdtools.models import CDIModel
 from typing import List, Union
 from cdtools.reconstructors import Reconstructor
 
+if TYPE_CHECKING:
+    from cdtools.models import CDIModel
+    from cdtools.datasets.ptycho_2d_dataset import Ptycho2DDataset
+    
+
 __all__ = ['SGDReconstructor']
 
 
@@ -43,11 +49,17 @@ class SGDReconstructor(Reconstructor):
                  dataset: Ptycho2DDataset,
                  subset: List[int] = None):
 
-        super().__init__(model, dataset, subset)
-
         # Define the optimizer for use in this subclass
-        self.optimizer = t.optim.SGD(self.model.parameters())
+        optimizer = t.optim.SGD(model.parameters())
 
+        super().__init__(
+            model,
+            dataset,
+            optimizer,
+            subset=subset,
+        )
+
+        
     def adjust_optimizer(self,
                          lr: int = 0.005,
                          momentum: float = 0,
@@ -82,7 +94,7 @@ class SGDReconstructor(Reconstructor):
 
     def optimize(self,
                  iterations: int,
-                 batch_size: int = None,
+                 batch_size: int = 15,
                  lr: float = 2e-7,
                  momentum: float = 0,
                  dampening: float = 0,
@@ -133,25 +145,20 @@ class SGDReconstructor(Reconstructor):
             Optional, enable/disable shuffling of the dataset. This option
             is intended for diagnostic purposes and should be left as True.
         """
-        # 1) The subset statement is contained in Reconstructor.__init__
 
-        # 2) Set up / re-initialize the data laoder
-        if batch_size is not None:
-            self.setup_dataloader(batch_size=batch_size, shuffle=shuffle)
-        else:
-            # Use default torch dataloader parameters
-            self.setup_dataloader(batch_size=1, shuffle=False)
-
-        # 3) The optimizer is created in self.__init__, but the
-        #    hyperparameters need to be set up with self.adjust_optimizer
+        # The optimizer is created in self.__init__, but the
+        # hyperparameters need to be set up with self.adjust_optimizer
         self.adjust_optimizer(lr=lr,
                               momentum=momentum,
                               dampening=dampening,
                               weight_decay=weight_decay,
                               nesterov=nesterov)
 
-        # 4) This is analagous to making a call to CDIModel.AD_optimize
-        return super(SGDReconstructor, self).optimize(iterations,
-                                                      regularization_factor,
-                                                      thread,
-                                                      calculation_width)
+        # Now, we run the optimize routine defined in the base class
+        return super(SGDReconstructor, self).optimize(
+            iterations,
+            batch_size=batch_size,
+            regularization_factor=regularization_factor,
+            thread=thread,
+            calculation_width=calculation_width,
+        )
diff --git a/tests/models/test_fancy_ptycho.py b/tests/models/test_fancy_ptycho.py
index 4182c93..8bc4d87 100644
--- a/tests/models/test_fancy_ptycho.py
+++ b/tests/models/test_fancy_ptycho.py
@@ -56,8 +56,8 @@ def test_lab_ptycho(lab_ptycho_cxi, reconstruction_device, show_plot):
         dataset,
         n_modes=3,
         oversampling=2,
-        exponentiate_obj=True,
         dm_rank=2,
+        exponentiate_obj=True,
         probe_support_radius=120,
         propagation_distance=5e-3,
         units='mm',
@@ -70,7 +70,7 @@ def test_lab_ptycho(lab_ptycho_cxi, reconstruction_device, show_plot):
     model.to(device=reconstruction_device)
     dataset.get_as(device=reconstruction_device)
 
-    for loss in model.Adam_optimize(70, dataset, lr=0.02, batch_size=10):
+    for loss in model.Adam_optimize(50, dataset, lr=0.02, batch_size=10):
         print(model.report())
         if show_plot and model.epoch % 10 == 0:
             model.inspect(dataset)
@@ -79,6 +79,11 @@ def test_lab_ptycho(lab_ptycho_cxi, reconstruction_device, show_plot):
         print(model.report())
         if show_plot and model.epoch % 10 == 0:
             model.inspect(dataset)
+            
+    for loss in model.Adam_optimize(25, dataset, lr=0.001, batch_size=50):
+        print(model.report())
+        if show_plot and model.epoch % 10 == 0:
+            model.inspect(dataset)
 
     model.tidy_probes()
 
diff --git a/tests/test_reconstructors.py b/tests/test_reconstructors.py
index 3995b6f..132a8c2 100644
--- a/tests/test_reconstructors.py
+++ b/tests/test_reconstructors.py
@@ -16,7 +16,8 @@ def test_Adam_gold_balls(gold_ball_cxi, reconstruction_device, show_plot):
         2) We are only using the single-GPU dataloading method
         3) Ensure `recon.model` points to the original `model`
         4) Reconstructions performed by `Adam.optimize` and
-           `model.Adam_optimize` calls produce identical results.
+           `model.Adam_optimize` calls produce identical results when
+           run over one round of optimization.
         5) The quality of the reconstruction remains below a specified
            threshold.
         5) Ensure that the FancyPtycho model works fine and dandy with the
@@ -91,7 +92,8 @@ def test_Adam_gold_balls(gold_ball_cxi, reconstruction_device, show_plot):
           ' reconstruction_device,', reconstruction_device)
     t.manual_seed(0)
 
-    for i, iterations in enumerate(epoch_tup):
+    # We only need to test the first loop to ensure it's identical
+    for i, iterations in enumerate(epoch_tup[:1]):
         for loss in model.Adam_optimize(iterations,
                                         dataset,
                                         lr=lr_tup[i],
@@ -106,14 +108,15 @@ def test_Adam_gold_balls(gold_ball_cxi, reconstruction_device, show_plot):
         model.inspect(dataset)
         model.compare(dataset)
 
-    # Ensure equivalency between the model reconstructions
-    assert np.allclose(model_recon.loss_history[-1], model.loss_history[-1])
+    # Ensure equivalency between the model reconstructions during the first
+    # pass, where they should be identical
+    assert np.allclose(model_recon.loss_history[:epoch_tup[0]], model.loss_history[:epoch_tup[0]])
 
     # Ensure reconstructions have reached a certain loss tolerance. This just
     # comes from running a reconstruction when it was working well and
     # choosing a rough value. If it triggers this assertion error, something
     # changed to make the final quality worse!
-    assert model.loss_history[-1] < 0.0001
+    assert model_recon.loss_history[-1] < 0.0001
 
 
 @pytest.mark.slow
@@ -127,7 +130,8 @@ def test_LBFGS_RPI(optical_data_ss_cxi,
            hyperparameters
         2) Ensure `recon.model` points to the original `model`
         3) Reconstructions performed by `LBFGS.optimize` and
-           `model.LBFGS_optimize` calls produce identical results.
+           `model.LBFGS_optimize` calls produce identical results when
+           run over one round of reconstruction.
         4) The quality of the reconstruction remains below a specified
            threshold.
         5) Ensure that the RPI model works fine and dandy with the
@@ -184,7 +188,7 @@ def test_LBFGS_RPI(optical_data_ss_cxi,
     print('Running reconstruction using CDIModel.LBFGS_optimize.' +
           'optimize on provided reconstruction_device,', reconstruction_device)
     t.manual_seed(0)
-    for i, iterations in enumerate(epoch_tup):
+    for i, iterations in enumerate(epoch_tup[:1]):
         for loss in model.LBFGS_optimize(iterations,
                                          dataset,
                                          lr=0.4,
@@ -198,12 +202,12 @@ def test_LBFGS_RPI(optical_data_ss_cxi,
         model.compare(dataset)
 
     # Check loss equivalency between the two reconstructions
-    assert np.allclose(model.loss_history[-1], model_recon.loss_history[-1])
+    assert np.allclose(model.loss_history[:epoch_tup[0]], model_recon.loss_history[:epoch_tup[0]])
 
     # The final loss when testing this was 2.28607e-3. Based on this, we set
     # a threshold of 2.3e-3 for the tested loss. If this value has been
     # exceeded, the reconstructions have gotten worse.
-    assert model.loss_history[-1] < 0.0023
+    assert model_recon.loss_history[-1] < 0.0023
 
 
 @pytest.mark.slow
@@ -214,7 +218,8 @@ def test_SGD_gold_balls(gold_ball_cxi, reconstruction_device, show_plot):
            hyperparameters
         3) Ensure `recon.model` points to the original `model`
         4) Reconstructions performed by `SGD.optimize` and
-           `model.SGD_optimize` calls produce identical results.
+           `model.SGD_optimize` calls produce identical results
+           when run over one round of reconstruction.
         5) The quality of the reconstruction remains below a specified
            threshold.
         5) Ensure that the FancyPtycho model works fine and dandy with the