Struct MASOptimizer 

pub struct MASOptimizer<O: Optimizer> { /* private fields */ }

Memory Aware Synapses optimizer

Estimates parameter importance using gradient magnitude at optimal parameters, avoiding the need for data from previous tasks.

Implementations

impl<O: Optimizer> MASOptimizer<O>

pub fn new( base_optimizer: O, params: Vec<Arc<RwLock<Tensor>>>, config: MASConfig, ) -> OptimizerResult<Self>

Create a new MAS optimizer

pub fn with_defaults( base_optimizer: O, params: Vec<Arc<RwLock<Tensor>>>, ) -> OptimizerResult<Self>

Create with default configuration

pub fn compute_importance(&mut self) -> OptimizerResult<()>

Compute importance using output gradient magnitude

pub fn consolidate_task(&mut self) -> OptimizerResult<()>

Consolidate task (save optimal parameters)

Trait Implementations

impl<O: Optimizer> Optimizer for MASOptimizer<O>

fn step(&mut self) -> OptimizerResult<()>

Perform a single optimization step

fn zero_grad(&mut self)

Zero all gradients

fn get_lr(&self) -> Vec<f32>

Get the current learning rate

fn set_lr(&mut self, lr: f32)

Set one learning rate for every parameter group (broadcast).

fn add_param_group( &mut self, params: Vec<Arc<RwLock<Tensor>>>, options: HashMap<String, f32>, )

Add a parameter group

fn parameters(&self) -> Vec<Arc<RwLock<Tensor>>>

Get the parameter tensors managed by this optimizer.

fn state_dict(&self) -> OptimizerResult<OptimizerState>

Get state dict for serialization

fn load_state_dict(&mut self, state: OptimizerState) -> OptimizerResult<()>

Load state dict

fn set_lrs(&mut self, lrs: &[f32])

Set the learning rate of each parameter group individually.