torch_sim.optimizers

Optimizers for geometry relaxations.

This module provides optimization algorithms for atomic structures in a batched format, enabling efficient relaxation of multiple atomic structures simultaneously. It uses a filter-based design where cell optimization constraints and parameterizations are handled by separate filter functions.

Classes

OPTIM_REGISTRY	dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list. For example: dict(one=1, two=2).
Optimizer	Enumeration of the optimization flavors.
ase_fire_key	str(object='') -> str str(bytes_or_buffer[, encoding[, errors]]) -> str
vv_fire_key	str(object='') -> str str(bytes_or_buffer[, encoding[, errors]]) -> str

Modules

cell_filters	Cell filters for optimization algorithms.
fire	FIRE (Fast Inertial Relaxation Engine) optimizer implementation.
gradient_descent	Gradient descent optimizer implementation.
state	Optimizer state classes.