ReptileOptions<T, TInput, TOutput>
Options & Configuration · AiDotNet.MetaLearning.Options
Configuration options for the Reptile meta-learning algorithm.
Inheritance: ModelOptions → ReptileOptions<T, TInput, TOutput>
Implements: IMetaLearnerOptions<T>
For Beginners
Reptile is the simplest meta-learning algorithm to understand:
- Train on a task for several steps
- Move the starting point slightly toward where you ended up
- Repeat with many tasks
After seeing many tasks, your starting point becomes great for learning any new task!
How It Works
Reptile is a simple first-order meta-learning algorithm that doesn’t require computing gradients through the adaptation process. Instead, it interpolates between current meta-parameters and adapted parameters.
Key difference from MAML: Reptile doesn’t compute gradients through adaptation. This makes it much simpler to implement and faster to run, with competitive performance.
Constructors
| Constructor | Summary |
|---|---|
ReptileOptions(IFullModel<T, TInput, TOutput> metaModel) |
Initializes a new instance of the ReptileOptions 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; } |
Gets or sets the optimizer for meta-parameter updates (outer loop). |
ILossFunction<T> LossFunction { get; set; } |
Loss function for meta-training; null uses the meta-model’s default loss. |
bool EnableCheckpointing { get; set; } |
Gets or sets whether to save checkpoints during training. |
bool UseFirstOrder { get; set; } |
Gets or sets whether to use first-order approximation. |
bool UseSerialUpdate { get; set; } |
Gets or sets whether to use the serial (single-task) or batched update variant. |
double InnerLearningRate { get; set; } |
Gets or sets the learning rate for the inner loop (task adaptation). |
double Interpolation { get; set; } |
Gets or sets the interpolation factor for meta-updates. |
double OuterLearningRate { get; set; } |
Gets or sets the learning rate for the outer loop (meta-update). |
double? FinalOuterLearningRate { get; set; } |
Gets or sets the outer step size that OuterLearningRate anneals to over training. |
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 InnerBatches { get; set; } |
Gets or sets the number of inner batches per adaptation step. |
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 Reptile options. |
bool IsValid() |
Validates that all Reptile configuration options are properly set. |