evox.algorithms.so.es_variants.esmc

Module Contents

Classes

ESMC

The implementation of the DES algorithm.

API

class evox.algorithms.so.es_variants.esmc.ESMC(pop_size: int, center_init: torch.Tensor, optimizer: Literal[adam] | None = None, sigma_decay: float = 1.0, sigma_limit: float = 0.01, lr: float = 0.05, sigma: float = 0.03, device: torch.device | None = None)[source]

Bases: evox.core.Algorithm

The implementation of the DES algorithm.

Reference: Learn2Hop: Learned Optimization on Rough Landscapes (https://proceedings.mlr.press/v139/merchant21a.html)

This code has been inspired by or utilizes the algorithmic implementation from evosax. More information about evosax can be found at the following URL: GitHub Link: https://github.com/RobertTLange/evosax

Initialization

Initialize the ESMC algorithm with the given parameters.

Parameters:

  • pop_size – The size of the population.

  • center_init – The initial center of the population. Must be a 1D tensor.

  • elite_ratio – The ratio of elite population. Defaults to 0.1.

  • lr – The learning rate for the optimizer. Defaults to 0.05.

  • sigma_decay – The decay factor for the standard deviation. Defaults to 1.0.

  • sigma_limit – The minimum value for the standard deviation. Defaults to 0.01.

  • optimizer – The optimizer to use. Defaults to None. Currently, only “adam” or None is supported.

  • device – The device to use for the tensors. Defaults to None.

step()[source]

One iteration of the ESMC algorithm.

This function will sample a population, evaluate their fitness, and then update the center and standard deviation of the algorithm using the sampled population.

record_step()[source]