Updated 9 months ago
nadir
Nadir: Cutting-edge PyTorch optimizers for simplicity & composability! 🔥🚀💻
Updated 9 months ago
metaperceptron
MetaPerceptron: A Standardized Framework For Metaheuristic-Driven Multi-layer Perceptron Optimization
adagrad-approach
adam-optimizer
adelta-optimizer
classification-models
genetic-algorithm
global-search
gradient-free-based-multi-layer-perceptron
metaheuristic-algorithms
metaheuristic-based-multi-layer-perceptron
metaheuristics
mlp
multi-layer-perceptron
nature-inspired-optimization
neural-network
particle-swarm-optimization
regression-models
sgd-optimizer
whale-optimization-algorithm
Updated 9 months ago
deforce
deforce: Derivative-Free Algorithms for Optimizing Cascade Forward Neural Networks
Updated 9 months ago
pyrddlgym-jax
JAX compilation of RDDL description files, and a differentiable planner in JAX.
automatic-differentiation
backpropagation
control
controller
differentiable-simulations
gradient-based-optimisation
jax
model-based-control
nonlinear-control
nonlinear-dynamics
nonlinear-optimization
planning
planning-algorithms
planning-domain-definition-language
policy-gradient
rddl
reinforcement-learning
sgd
sgd-optimizer
stochastic-gradient-descent
Updated 9 months ago
delicoco-ieee-transactions
In compressed decentralized optimization settings, there are benefits to having multiple gossip steps between subsequent gradient iterations, even when the cost of doing so is appropriately accounted for e.g. by means of reducing the precision of compressed information.