[ICML 2025] Official Pytorch code for "SASSHA: Sharpness-aware Adaptive Second-order Optimization With Stable Hessian Approximation"
☆23Aug 11, 2025Updated 6 months ago
Alternatives and similar repositories for Sassha
Users that are interested in Sassha are comparing it to the libraries listed below
Sorting:
- ☆17Nov 10, 2025Updated 3 months ago
- [UAI 2025] Official code for reproducing paper "Critical Influence of Overparameterization on Sharpness-aware Minimization"☆19May 14, 2025Updated 9 months ago
- ☆28Feb 21, 2025Updated last year
- Official implementation of "Multi-armed Bandit Algorithm against Strategic Replication"☆14May 17, 2022Updated 3 years ago
- A Signal Propagation Perspective for Pruning Neural Networks at Initialization☆14Jun 23, 2020Updated 5 years ago
- Official PyTorch implementation of "Robust Deep Learning from Crowds with Belief Propagation"☆19Mar 22, 2022Updated 3 years ago
- Official PyTorch implementation of "A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning"☆28Oct 12, 2022Updated 3 years ago
- Official implementation for the paper "Controlled Sparsity via Constrained Optimization"☆11Aug 10, 2022Updated 3 years ago
- ☆24Oct 24, 2021Updated 4 years ago
- Soft Threshold Weight Reparameterization for Learnable Sparsity☆91Feb 15, 2023Updated 3 years ago
- [AAAI 2023] Official implementation of 'Anonymization for Skeleton Action Recognition'☆29Dec 29, 2022Updated 3 years ago
- A generic code base for neural network pruning, especially for pruning at initialization.☆31Sep 3, 2022Updated 3 years ago
- Implementation of Effective Sparsification of Neural Networks with Global Sparsity Constraint☆31Mar 24, 2022Updated 3 years ago
- Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025☆33May 1, 2025Updated 9 months ago
- ☆40Nov 22, 2025Updated 3 months ago
- DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures☆32Aug 13, 2020Updated 5 years ago
- APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention☆271Nov 29, 2025Updated 3 months ago
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆64Aug 23, 2023Updated 2 years ago
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆63Mar 11, 2025Updated 11 months ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆89May 20, 2024Updated last year
- Code and checkpoints of compressed networks for the paper titled "HYDRA: Pruning Adversarially Robust Neural Networks" (NeurIPS 2020) (ht…☆91Dec 22, 2022Updated 3 years ago
- ☆621Feb 20, 2026Updated last week
- ☆252Dec 2, 2024Updated last year
- ☆195Feb 20, 2026Updated last week
- Concept Bottleneck Models, ICML 2020☆240Feb 24, 2023Updated 3 years ago
- ☆234Feb 12, 2025Updated last year
- ☆292Jul 15, 2024Updated last year
- End-to-end training of sparse deep neural networks with little-to-no performance loss.☆335Jan 26, 2023Updated 3 years ago
- Awesome LLM compression research papers and tools.☆1,780Updated this week
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆452May 13, 2025Updated 9 months ago
- Implementations of ideas from recent papers☆392Dec 22, 2020Updated 5 years ago
- SAM: Sharpness-Aware Minimization (PyTorch)☆1,963Feb 21, 2024Updated 2 years ago
- TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)☆553Mar 30, 2023Updated 2 years ago
- Summary, Code for Deep Neural Network Quantization☆558Jun 14, 2025Updated 8 months ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆693Jan 26, 2026Updated last month
- A curated list of neural network pruning resources.☆2,490Apr 4, 2024Updated last year
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆775Jul 10, 2025Updated 7 months ago
- Long Range Arena for Benchmarking Efficient Transformers☆778Dec 16, 2023Updated 2 years ago
- RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]☆770Mar 31, 2025Updated 11 months ago