uqregressors.bayesian.dropout
Monte Carlo Dropout is implemented as in Gal and Ghahramani 2016.
Monte Carlo Dropout
This module implements a Monte Carlo (MC) Dropout Regressor for regression on a one dimensional output with uncertainty quantification. It estimates predictive uncertainty by performing multiple stochastic forward passes through a dropout-enabled neural network.
Key features are
- Customizable neural network architecture
- Aleatoric uncertainty included with hyperparameter tau
- Prediction Intervals based on Gaussian assumption
- Customizable optimizer and loss function
- Optional Input/Output Normalization
Warning
Using hyperparameter optimization to optimize the aleatoric uncertainty hyperparameter tau is often necessary to obtain correct predictive intervals!
MCDropoutRegressor
Bases: BaseEstimator
, RegressorMixin
MC Dropout Regressor with uncertainty estimation using neural networks.
This class trains a dropout MLP and takes stochastic forward passes to provide predictive uncertainty intervals. It makes a Gaussian assumption on the output distribution, and often requires tuning of the hyperparameter tau
Parameters:
Name | Type | Description | Default |
---|---|---|---|
name
|
str
|
Name of the model instance. |
'MC_Dropout_Regressor'
|
hidden_sizes
|
List[int]
|
Hidden layer sizes for the MLP. |
[64, 64]
|
dropout
|
float
|
Dropout rate to apply after each hidden layer. |
0.1
|
tau
|
float
|
Precision parameter (used in predictive variance). |
1e-06
|
use_paper_weight_decay
|
bool
|
Whether to use paper's theoretical weight decay. |
True
|
alpha
|
float
|
Significance level (1 - confidence level) for prediction intervals. |
0.1
|
requires_grad
|
bool
|
Whether to track gradients in prediction output. |
False
|
activation_str
|
str
|
Activation function name (e.g., "ReLU", "Tanh"). |
'ReLU'
|
n_samples
|
int
|
Number of stochastic forward passes for prediction. |
100
|
learning_rate
|
float
|
Learning rate for the optimizer. |
0.001
|
epochs
|
int
|
Number of training epochs. |
200
|
batch_size
|
int
|
Batch size for training. |
32
|
optimizer_cls
|
Optimizer
|
PyTorch optimizer class. |
Adam
|
optimizer_kwargs
|
dict
|
Optional kwargs to pass to optimizer. |
None
|
scheduler_cls
|
Optional[Callable]
|
Optional learning rate scheduler class. |
None
|
scheduler_kwargs
|
dict
|
Optional kwargs for the scheduler. |
None
|
loss_fn
|
Callable
|
Loss function for training (default: MSE). |
mse_loss
|
device
|
str
|
Device to run training/prediction on ("cpu" or "cuda"). |
'cpu'
|
use_wandb
|
bool
|
If True, logs training to Weights & Biases. |
False
|
wandb_project
|
str
|
W&B project name. |
None
|
wandb_run_name
|
str
|
W&B run name. |
None
|
random_seed
|
Optional[int]
|
Seed for reproducibility. |
None
|
scale_data
|
bool
|
Whether to standardize inputs and outputs. |
True
|
input_scaler
|
Optional[TorchStandardScaler]
|
Custom input scaler. |
None
|
output_scaler
|
Optional[TorchStandardScaler]
|
Custom output scaler. |
None
|
tuning_loggers
|
List[Logger]
|
External loggers returned from hyperparameter tuning. |
[]
|
Attributes:
Name | Type | Description |
---|---|---|
model |
MLP
|
Trained PyTorch MLP model. |
input_dim |
int
|
Dimensionality of input features. |
_loggers |
Logger
|
Training logger. |
training_logs |
Logs from training. |
|
tuning_logs |
Logs from hyperparameter tuning. |
Source code in uqregressors\bayesian\dropout.py
64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 |
|
fit(X, y)
Fit the MC Dropout model on training data.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X
|
array - like
|
Training features of shape (n_samples, n_features). |
required |
y
|
array - like
|
Target values of shape (n_samples,). |
required |
Source code in uqregressors\bayesian\dropout.py
171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 |
|
load(path, device='cpu', load_logs=False)
classmethod
Load a saved MC dropout regressor from disk.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
path
|
str or Path
|
Directory path to load the model from. |
required |
device
|
str or device
|
Device to load the model onto. |
'cpu'
|
load_logs
|
bool
|
Whether to load training and tuning logs. |
False
|
Returns:
Type | Description |
---|---|
MCDropoutRegressor
|
Loaded model instance. |
Source code in uqregressors\bayesian\dropout.py
339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 |
|
predict(X)
Predicts the target values with uncertainty estimates.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X
|
ndarray
|
Feature matrix of shape (n_samples, n_features). |
required |
Returns:
Type | Description |
---|---|
Union[Tuple[ndarray, ndarray, ndarray], Tuple[Tensor, Tensor, Tensor]]
|
Tuple containing: mean predictions, lower bound of the prediction interval, upper bound of the prediction interval. |
Note
If requires_grad
is False, all returned arrays are NumPy arrays.
Otherwise, they are PyTorch tensors with gradients.
Source code in uqregressors\bayesian\dropout.py
245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 |
|
save(path)
Save model weights, config, and scalers to disk.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
path
|
str or Path
|
Directory to save model components. |
required |
Source code in uqregressors\bayesian\dropout.py
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 |
|
MLP
Bases: Module
A simple feedforward neural network with dropout for regression.
This MLP supports customizable hidden layer sizes, activation functions, and dropout. It outputs a single scalar per input — the predictive mean.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
input_dim
|
int
|
Number of input features. |
required |
hidden_sizes
|
list of int
|
Sizes of the hidden layers. |
required |
dropout
|
float
|
Dropout rate (applied after each activation). |
required |
activation
|
callable
|
Activation function (e.g., nn.ReLU). |
required |
Source code in uqregressors\bayesian\dropout.py
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
|