Optimizer class abstract

The abstract base class for all optimization algorithms. Tracks a collection of trainable parameters and manages optimization steps and gradient resets.

Implementers

• Adagrad
• Adam
• AdamW
• AMSGrad
• Momentum
• NAG
• RMSprop
• SGD

Constructors

Optimizer(List<Tensor> parameters, double learningRate)

Base constructor initializing the target parameters and learningRate.

Properties

hashCode → int

The hash code for this object.

no setter, inherited

learningRate ↔ double

The step size factor applied during parameter updates.

getter/setter pair

parameters ↔ List<Tensor>

The collection of trainable parameter tensors managed by this optimizer.

getter/setter pair

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

step() → void

Executes a single optimization step to update all parameters in place.

toString() → String

A string representation of this object.

inherited

zeroGrad() → void

Clears gradients by resetting the gradient buffer of every managed tensor in parameters to 0.0.

Operators

operator ==(Object other) → bool

The equality operator.

inherited