Sparse Double Descent

Name: hezheug/sparse-double-descent
Author: hezheug

This framework implements key experiments on the sparse double descent phenomenon, as demonstrated in the following paper:

This framework implements key experiments on the sparse double descent phenomenon, as demonstrated in the following paper:

Features

Weight Pruning - Analysis of sparse double descent and overfitting in pruning.

Alternative open-source pentru Sparse Double Descent

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Sparse Double Descent.

tencent/pocketflow
Tencent/PocketFlow
2,914Vezi pe GitHub
PocketFlow is an integrated toolkit for deep learning model compression, distributed training, and mobile format optimization. It provides a system for reducing the size and complexity of neural networks to improve inference efficiency, featuring a dedicated engine for knowledge distillation and a mobile model optimizer. The framework differentiates itself through an automated hyperparameter tuning system that uses reinforcement learning and statistical models to determine optimal compression ratios and layer-wise bit allocation. It also includes a distributed training system that utilizes mu
Pythonautomlcomputer-visiondeep-learning
Vezi pe GitHub2,914
chrundle/biprop
chrundle/biprop
51Vezi pe GitHub
This method identifies a binary weight or binary weight and activation subnetwork within a randomly initialized network that achieves performance comparable to, and sometimes better than, a weight-optimized network. The resulting binarized and pruned networks that achieve comparable performance…
Python
Vezi pe GitHub51
dchiji-ntt/iterand
dchiji-ntt/iterand
10Vezi pe GitHub
by Daiki Chijiwa\*, Shin’ya Yamaguchi, Yasutoshi Ida, Kenji Umakoshi, Tomohiro Inoue
Python
Vezi pe GitHub10

Întrebări frecvente

Ce face hezheug/sparse-double-descent?

This framework implements key experiments on the sparse double descent phenomenon, as demonstrated in the following paper:

Care sunt principalele funcționalități ale hezheug/sparse-double-descent?

Principalele funcționalități ale hezheug/sparse-double-descent sunt: Weight Pruning.

Care sunt câteva alternative open-source pentru hezheug/sparse-double-descent?

Alternativele open-source pentru hezheug/sparse-double-descent includ: tencent/pocketflow — PocketFlow is an integrated toolkit for deep learning model compression, distributed training, and mobile format… chrundle/biprop — This method identifies a binary weight or binary weight and activation subnetwork within a randomly initialized… dchiji-ntt/iterand — by Daiki Chijiwa\*, Shin’ya Yamaguchi, Yasutoshi Ida, Kenji Umakoshi, Tomohiro Inoue. dem123456789/pruning-deep-neural-networks-from-a-sparsity-perspective — [ICLR 2023] Pruning Deep Neural Networks from a Sparsity Perspective. densoitlab/bitprune — This is the official repo for ICLR 2023 Paper "Bit-Pruning: A Sparse Multiplication-Less Dot-Product" Yusuke Sekikawa… boone891214/sanity-check-lth — Sample code use for NeurIPS 2021 paper: Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the…

hezheugsparse-double-descent

Features

Istoric stele

hezheugsparse-double-descent