Crate axonml_optim 

axonml-optim - Optimization Algorithms

Provides optimizers for training neural networks, including:

• SGD with momentum and Nesterov acceleration
• Adam and AdamW
• RMSprop
• Learning rate schedulers

Example

use axonml_optim::prelude::*;
use axonml_nn::{Linear, Module, Sequential};

// Create model
let model = Sequential::new()
    .add(Linear::new(784, 128))
    .add(Linear::new(128, 10));

// Create optimizer
let mut optimizer = Adam::new(model.parameters(), 0.001);

// Training loop
for epoch in 0..100 {
    let output = model.forward(&input);
    let loss = compute_loss(&output, &target);

    optimizer.zero_grad();
    loss.backward();
    optimizer.step();
}

@version 0.1.0 @author AutomataNexus Development Team

Re-exports

pub use adam::Adam;

pub use adam::AdamW;

pub use lr_scheduler::CosineAnnealingLR;

pub use lr_scheduler::ExponentialLR;

pub use lr_scheduler::LRScheduler;

pub use lr_scheduler::MultiStepLR;

pub use lr_scheduler::OneCycleLR;

pub use lr_scheduler::ReduceLROnPlateau;

pub use lr_scheduler::StepLR;

pub use lr_scheduler::WarmupLR;

pub use optimizer::Optimizer;

pub use rmsprop::RMSprop;

pub use sgd::SGD;

Modules

adam

Adam Optimizer - Adaptive Moment Estimation

lr_scheduler

Learning Rate Schedulers

optimizer

Optimizer Trait - Core Optimizer Interface

prelude

Common imports for optimization.

rmsprop

RMSprop Optimizer

sgd

SGD Optimizer - Stochastic Gradient Descent