DynamicTaskSamplingOptions<T, TInput, TOutput>

Options & Configuration ยท AiDotNet.MetaLearning.Options

Configuration options for the DynamicTaskSampling algorithm.

Inheritance: ModelOptions โ†’ DynamicTaskSamplingOptions<T, TInput, TOutput>

Implements: IMetaLearnerOptions<T>

How It Works

DynamicTaskSampling maintains per-task difficulty estimates and uses them to reweight the meta-gradient. Tasks with higher difficulty (loss after adaptation) receive higher weights via a softmax-based difficulty-proportional weighting, focusing meta-learning on tasks that the model struggles with most.

Constructors

Constructor Summary
DynamicTaskSamplingOptions(IFullModel<T, TInput, TOutput> metaModel) Creates options for meta-learning metaModel, with the default settings.

Properties

Property Summary
IEpisodicDataLoader<T, TInput, TOutput> DataLoader { get; set; } Episodic data loader that supplies the meta-training tasks; null when tasks are passed to training directly.
IFullModel<T, TInput, TOutput> MetaModel { get; set; } The model whose parameters the meta-learner trains to adapt quickly to new tasks.
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 default multi-class classification loss.
bool EnableCheckpointing { get; set; }
bool UseFirstOrder { get; set; } Whether to use the first-order approximation of the meta-gradient.
double DifficultyDecay { get; set; } EMA decay for tracking per-task difficulty (running mean of query losses).
double ExplorationCoeff { get; set; } Exploration coefficient (UCB-style) added to difficulty for exploration.
double InnerLearningRate { get; set; }
double OuterLearningRate { get; set; }
double TaskTemperature { get; set; } Temperature for difficulty-weighted gradient scaling.
double? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; }
int CheckpointFrequency { get; set; }
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int MetaBatchSize { get; set; }
int NumMetaIterations { get; set; }
int? RandomSeed { get; set; }

Methods

Method Summary
IMetaLearnerOptions<T> Clone()
bool IsValid()