My Master's Thesis on Variational Optimization of Neural Networks written at the Technical University of Denmark
-
Updated
Dec 1, 2021 - TeX
My Master's Thesis on Variational Optimization of Neural Networks written at the Technical University of Denmark
Approximate Natural Gradient Descent with precision weighted predictive coding
Project definition and implementations for Convex Optimization Course
Faster large mini-batch distributed training w/o. squeezing devices
(CEC2023 Tutorial) Foundations and Recent Advances on Natural Evolution Strategies
(EvoApps2022) "Towards a Principled Learning Rate Adaptation for Natural Evolution Strategies"
Matrix-multiplication-only KFAC; Code for ICML 2023 paper on Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning
High-performance implementations of several reinforcement learning algorithms and some commonly used benchmark problems (Matlab & C++)
Simple Experiments mainly on Machine Learning
Code for the paper "Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift"
(CEC2022) Fast Moving Natural Evolution Strategy for High-Dimensional Problems
Actor Critic using Kronecker-Factored Trust Region
Natural Gradient, Variational Inference
TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".
About A collection of AWESOME things about information geometry Topics
Gaussian Process package based on data augmentation, sparsity and natural gradients
Natural Gradient Boosting for Probabilistic Prediction
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).
Add a description, image, and links to the natural-gradients topic page so that developers can more easily learn about it.
To associate your repository with the natural-gradients topic, visit your repo's landing page and select "manage topics."