LOG-postech / SasshaLinks
[ICML 2025] Official Pytorch code for "SASSHA: Sharpness-aware Adaptive Second-order Optimization With Stable Hessian Approximation"
β20Updated last month
Alternatives and similar repositories for Sassha
Users that are interested in Sassha are comparing it to the libraries listed below
Sorting:
- [UAI 2025] Official code for reproducing paper "Critical Influence of Overparameterization on Sharpness-aware Minimization"β19Updated 4 months ago
- π¨ Malet (Machine Learning Experiment Tool) is a tool for efficient machine learning experiment execution, logging, analysis, and plot maβ¦β17Updated 5 months ago
- β17Updated 6 months ago
- β28Updated 7 months ago
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networksβ758Updated 2 months ago
- β25Updated last year
- β17Updated 2 years ago
- [KDD 2023] code for "Test accuracy vs. generalization gap: model selection in NLP without accessing training or testing data" https://arxβ¦β12Updated 2 years ago
- [NeurIPS 2021] code for "Taxonomizing local versus global structure in neural network loss landscapes" https://arxiv.org/abs/2107.11228β19Updated 3 years ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvatureβ162Updated 3 months ago
- PyTorch implementation of Mixer-nano (#parameters is 0.67M, originally Mixer-S/16 has 18M) with 90.83 % acc. on CIFAR-10. Training from sβ¦β35Updated 3 years ago
- A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...β363Updated last week
- Efficient PyTorch Hessian eigendecomposition tools!β378Updated last year
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorchβ341Updated last year
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]β28Updated 2 years ago
- [ICLR 2024] Dynamic Sparse Training with Structured Sparsityβ18Updated last year
- This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks"β¦β333Updated last year
- Neural Tangent Kernel Papersβ116Updated 8 months ago
- Pytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.β110Updated 6 years ago
- Pretrained models on CIFAR10/100 in PyTorchβ366Updated 4 months ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".β104Updated 2 years ago
- Code reproducing Neural Collapse phenomenon on MSE and cross-entropy lossβ14Updated 3 years ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)β16Updated 6 years ago
- tiny-imagenet dataset downloader & reader using tensorflow_datasets (tfds) apiβ20Updated 6 years ago
- β227Updated last year
- Comparison of method "Pruning at initialization prior to training" (Synflow/SNIP/GraSP) in PyTorchβ17Updated last year
- PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 witβ¦β198Updated last year
- β193Updated 4 years ago
- Lightweight torch implementation of rigl, a sparse-to-sparse optimizer.β57Updated 3 years ago
- Implementation of Continuous Sparsification, a method for pruning and ticket search in deep networksβ33Updated 3 years ago