natural-gradients
There are 19 repositories under natural-gradients topic.
ikostrikov/pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
stanfordmlgroup/ngboost
Natural Gradient Boosting for Probabilistic Prediction
theogf/AugmentedGaussianProcesses.jl
Gaussian Process package based on data augmentation, sparsity and natural gradients
nocotan/awesome-information-geometry
About A collection of AWESOME things about information geometry Topics
pomonam/NoisyNaturalGradient
TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".
gd-zhang/noisy-K-FAC
Natural Gradient, Variational Inference
gd-zhang/ACKTR
Actor Critic using Kronecker-Factored Trust Region
nomuramasahir0/crfmnes
(CEC2022) Fast Moving Natural Evolution Strategy for High-Dimensional Problems
Feuermagier/Beyond_Deep_Ensembles
Code for the paper "Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift"
Ankur-Deka/Machine-Learning-Notebooks
Simple Experiments mainly on Machine Learning
hiili/rlcc
High-performance implementations of several reinforcement learning algorithms and some commonly used benchmark problems (Matlab & C++)
yorkerlin/StructuredNGD-DL
Matrix-multiplication-only KFAC; Code for ICML 2023 paper on Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning
nomuramasahir0/cec2023-tutorial
(CEC2023 Tutorial) Foundations and Recent Advances on Natural Evolution Strategies
nomuramasahir0/xnes-adaptive-lr
(EvoApps2022) "Towards a Principled Learning Rate Adaptation for Natural Evolution Strategies"
andreofner/PredProp
Approximate Natural Gradient Descent with precision weighted predictive coding
erfanloghmani/Convex-Optimization-Project
Project definition and implementations for Convex Optimization Course
JakobHavtorn/Master-Thesis
My Master's Thesis on Variational Optimization of Neural Networks written at the Technical University of Denmark
SuperbTUM/Faster-Distributed-Training
Faster large mini-batch distributed training w/o. squeezing devices