SEALOptions<T, TInput, TOutput>

Options & Configuration · AiDotNet.MetaLearning.Options

Configuration options for the SEAL (Sample-Efficient Adaptive Learning) meta-learning algorithm.

Inheritance: ModelOptions → SEALOptions<T, TInput, TOutput>

Implements: IMetaLearnerOptions<T>

For Beginners

SEAL learns the best starting point for a model so that it can quickly adapt to new tasks with minimal data. Think of it like learning how to learn - after seeing many tasks, the model knows how to pick up new skills quickly.

Imagine learning to play musical instruments:

  • Learning your first instrument (piano) is hard
  • Learning your second instrument (guitar) is easier
  • By your 5th instrument, you’ve learned principles that help you

pick up any new instrument much faster

SEAL does the same with machine learning models!

How It Works

SEAL is a gradient-based meta-learning algorithm that combines ideas from MAML with sample-efficiency improvements. It learns initial parameters that can be quickly adapted to new tasks with just a few examples, incorporating temperature scaling, entropy regularization, and optional adaptive learning rates.

Key features of SEAL:

  • Temperature scaling: Controls confidence in predictions during meta-training
  • Entropy regularization: Encourages diverse predictions to prevent overconfident models
  • Adaptive learning rates: Per-parameter learning rate adaptation based on gradient norms
  • Weight decay: Prevents overfitting to meta-training tasks

Constructors

Constructor Summary
SEALOptions(IFullModel<T, TInput, TOutput> metaModel) Initializes a new instance of the SEALOptions class with the required meta-model.

Properties

Property Summary
IEpisodicDataLoader<T, TInput, TOutput> DataLoader { get; set; } Gets or sets the episodic data loader for sampling tasks.
IFullModel<T, TInput, TOutput> MetaModel { get; set; } Gets or sets the meta-model to be trained.
IGradientBasedOptimizer<T, TInput, TOutput> InnerOptimizer { get; set; } Optimizer for task adaptation.
IGradientBasedOptimizer<T, TInput, TOutput> MetaOptimizer { get; set; } Optimizer for the meta-update.
ILossFunction<T> LossFunction { get; set; } Loss function for meta-training; null uses the meta-model’s default loss.
SEALAdaptiveLearningRateMode AdaptiveLearningRateMode { get; set; } Gets or sets the mode for adaptive learning rate computation.
bool EnableCheckpointing { get; set; } Gets or sets whether to save checkpoints during training.
bool EntropyOnlyDuringMetaTrain { get; set; } Gets or sets whether to apply entropy regularization only during meta-training.
bool UseAdaptiveInnerLR { get; set; } Gets or sets whether to use adaptive inner learning rates.
bool UseFirstOrder { get; set; } Gets or sets whether to use first-order approximation (FOMAML-style).
double AdaptiveLearningRateDecay { get; set; } Gets or sets the decay rate for running mean in adaptive learning rates.
double AdaptiveLearningRateEpsilon { get; set; } Gets or sets the epsilon value for numerical stability in adaptive learning rates.
double EntropyCoefficient { get; set; } Gets or sets the entropy regularization coefficient.
double InnerLearningRate { get; set; } Gets or sets the learning rate for the inner loop (task adaptation).
double MinTemperature { get; set; } Gets or sets the minimum temperature for temperature annealing.
double OuterLearningRate { get; set; } Gets or sets the learning rate for the outer loop (meta-optimization).
double Temperature { get; set; } Gets or sets the temperature scaling factor for the loss function.
double WeightDecay { get; set; } Gets or sets the weight decay (L2 regularization) coefficient.
double? GradientClipThreshold { get; set; } Gets or sets the maximum gradient norm for gradient clipping.
int AdaptationSteps { get; set; } Gets or sets the number of gradient steps to take during inner loop adaptation.
int CheckpointFrequency { get; set; } Gets or sets how often to save checkpoints.
int EvaluationFrequency { get; set; } Gets or sets how often to evaluate during meta-training.
int EvaluationTasks { get; set; } Gets or sets the number of tasks to use for evaluation.
int MetaBatchSize { get; set; } Gets or sets the number of tasks to sample per meta-training iteration.
int NumMetaIterations { get; set; } Gets or sets the total number of meta-training iterations to perform.
int? RandomSeed { get; set; } Gets or sets the random seed for reproducibility.

Methods

Method Summary
IMetaLearnerOptions<T> Clone() Creates a deep copy of the SEAL options.
bool IsValid() Validates that all SEAL configuration options are properly set.