Pytorch implementation of preconditioned stochastic gradient descent (affine group preconditioner, low-rank approximation preconditioner and more)

Fine-tuning of diffusion models

LoRA (Low-Rank Adaptation) inspector for Stable Diffusion

VIP is a python package/library for angular, reference star and spectral differential imaging for exoplanet/disk detection through high-contrast imaging.

Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression. CVPR2020.

A framework based on the tensor train decomposition for working with multivariate functions and multidimensional arrays

Tensorflow implementation of preconditioned stochastic gradient descent

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

[ICLR 2022] Code for paper "Exploring Extreme Parameter Compression for Pre-trained Language Models"(https://arxiv.org/abs/2205.10036)

Pytorch implemenation of "Learning Filter Basis for Convolutional Neural Network Compression" ICCV2019

Solver in the low-rank tensor train format with cross approximation approach for the multidimensional Fokker-Planck equation

MUSCO: Multi-Stage COmpression of neural networks

My experiment of multilayer NMF, a deep neural network in which the first several layers take Semi-NMF as its pseudo-activation-function that finds the latent sturcture embedding in the original data unsupervisely.

Lowrankdensity

Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce significant latency. We propose a compression method that leverages low rank matrix factorization durin…

The repository contains code to reproduce the experiments from our paper Error Feedback Can Accurately Compress Preconditioners available below:

Linear Algebra project `Decomposition into Low-Rank and Sparse Matrices in Computer Vision` | Applied Sciences Faculty, UCU (2019)

Numerical experiments for Optima-TT method from teneva python package. This method finds items which relate to min and max elements of the tensor in the tensor train (TT) format.

Gaussian Mixture Model with low rank approximation

Proyecto para el Trabajo Final de Grado: Aplicación de técnicas de inteligencia artificial para la generación automática de escenarios a partir de lenguaje natural.