kl-divergence

A pytorch package for non-negative matrix factorization.

IJCAI 2021, "Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation"

A PyTorch Implementation of Generating Sentences from a Continuous Space by Bowman et al. 2015.

This repository summarizes techniques for KL divergence vanishing problem.

Repository for "Blending Data-Driven Priors in Dynamic Games" - RSS 2024

This repository contains the lab work for Coursera course on "Generative AI with Large Language Models".

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

Experiments with variational autoencoders in Julia

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

PyTorch implementations of the beta divergence loss.

Code for "EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL" (arxiv.org/abs/2602.04417)

A self-distillation based training method for long context reasoning in a single LLM without reinforcement learning

KL-loss

PyTorch implementation of α-geodesical skew divergence

Autonomous Agent Shannon Entropy, Mutual Information, Kullback-Leibler Divergence & Jensen-Shannon Estimator

Autonomous Agent Shannon Entropy, Mutual Information, Kullback-Leibler Divergence & Jensen-Shannon Estimator

Machine Learning algorithms built from scratch for AMMI Machine Learning course

Forward and reverse KL divergence monitor detecting policy drift and reward hacking across distributions

Forward and reverse KL divergence monitor detecting policy drift and reward hacking across distributions

ORDA: Triton kernels for logit-level knowledge distillation loss.