A pytorch package for non-negative matrix factorization.
gpu pytorch nmf em-algorithm kl-divergence nonnegative-matrix-factorization 1d-convolution beta-divergence plca siplca
- Updated
- Python
#
kl-divergence
Here are 56 public repositories matching this topic...
IJCAI 2021, "Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation"
- Updated
- Jupyter Notebook
A PyTorch Implementation of Generating Sentences from a Continuous Space by Bowman et al. 2015.
- Updated
- Python
This repository summarizes techniques for KL divergence vanishing problem.
- Updated
- Python
Repository for "Blending Data-Driven Priors in Dynamic Games" - RSS 2024
game-theory flax autonomous-driving trajectory-optimization multi-modal car-racing kl-divergence jax stochastic-game data-aware policy-blending data-driven-game
- Updated
- Python
Experiments with variational autoencoders in Julia
flux machine machine-learning-algorithms julia-language dataset vae variational-autoencoder kl-divergence
- Updated
- Julia
Implementations of basic concepts dealt under the Reinforcement Learning umbrella. This project is collection of assignments in CS747: Foundations of Intelligent and Learning Agents (Autumn 2017) at IIT Bombay
reinforcement-learning linear-programming thompson-sampling epsilon-greedy ucb policy-evaluation mdps multi-armed-bandits policy-iteration randomised-algorithms reinforcement-learning-excercises kl-divergence markovian-epidemic-processes reinforcement-learning-analysis multiarm-bandit ucb1 howards-pi batch-switching randomized-policy-iteration
- Updated
- Python
This repository contains the lab work for Coursera course on "Generative AI with Large Language Models".
reinforcement-learning transformer kl-divergence proximal-policy-optimization large-language-models prompt-engineering flan-t5 instruction-finetuning low-rank-adaptation reward-model parameter-efficient-fine-tuning llm-evaluation
- Updated
- Jupyter Notebook
Code for enumerating and evaluating numerical methods for Langevin dynamics using near-equilibrium estimates of the KL-divergence. Accompanies https://doi.org/10.3390/e20050318
- Updated
- Jupyter Notebook
PyTorch implementation of α-geodesical skew divergence
- Updated
- Python
PyTorch implementations of the beta divergence loss.
numpy torch pytorch kullback-leibler-divergence distance-measures distance-metric nmf loss-functions loss kl-divergence divergence non-negative-matrix-factorization mean-square-error nmf-decomposition objective-functions beta-divergence distance-metrics divergences mean-squared-error itakura-saito-divergence
- Updated
- Python
A self-distillation based training method for long context reasoning in a single LLM without reinforcement learning
- Updated
- Python
Machine Learning algorithms built from scratch for AMMI Machine Learning course
linear-regression naive-bayes-classifier kmeans-clustering coordinate-descent kl-divergence perceptron-learning-algorithm kfold-cross-validation gaussian-discriminant-analysis
- Updated
- Jupyter Notebook
Code for "EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL" (arxiv.org/abs/2602.04417)
- Updated
- Python
My MSc project on applying, tuning and modifying the PPO and A2C algorithms to Pettingzoo MARL library two player poker game
- Updated
- Python
Relative entropy, mutual information, KL divergence of 2 given Images 🖼
- Updated
- Jupyter Notebook
- Updated
- Jupyter Notebook
Basic GANs with variety of loss functions as an exercise for my Thesis with Prof. Randy Paffenroth. KL, Reverse-KL, JS and Wasserstein GAN.
deep-neural-networks generative-adversarial-network gan kullback-leibler-divergence jensen-shannon-divergence kl-divergence synthetic-data wasserstein-gans
- Updated
- Jupyter Notebook
Change point detection using KL divergence
- Updated
- Python
Improve this page
Add a description, image, and links to the kl-divergence topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the kl-divergence topic, visit your repo's landing page and select "manage topics."