he-zh / sparse-double-descentLinks
This framework implements key experiments on the sparse double descent phenomenon (ICML 2022).
☆15Updated 3 years ago
Alternatives and similar repositories for sparse-double-descent
Users that are interested in sparse-double-descent are comparing it to the libraries listed below
Sorting:
- [ICLR 2021 Spotlight Oral] "Undistillable: Making A Nasty Teacher That CANNOT teach students", Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Che…☆82Updated 4 years ago
- A Closer Look at Accuracy vs. Robustness☆88Updated 4 years ago
- [NeurIPS 2020] "Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free" by Haotao Wang*, Tianlong C…☆44Updated 4 years ago
- ☆108Updated 3 years ago
- Code and checkpoints of compressed networks for the paper titled "HYDRA: Pruning Adversarially Robust Neural Networks" (NeurIPS 2020) (ht…☆91Updated 3 years ago
- Implementation of Effective Sparsification of Neural Networks with Global Sparsity Constraint☆31Updated 3 years ago
- Code to reproduce experiments from 'Does Knowledge Distillation Really Work' a paper which appeared in the 2021 NeurIPS proceedings.☆33Updated 2 years ago
- 🔬 Some personal research code on analyzing CNNs. Started with a thorough exploration of Stanford's Tiny-Imagenet-200 dataset.☆105Updated 6 years ago
- Accompanying code for the paper "Zero-shot Knowledge Transfer via Adversarial Belief Matching"☆144Updated 5 years ago
- "Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness" (NeurIPS 2020).☆52Updated 5 years ago
- ☆58Updated 2 years ago
- PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)☆144Updated 3 years ago
- ICLR 2021, Fair Mixup: Fairness via Interpolation☆59Updated 4 years ago
- Code for our paper "Regularizing Neural Networks via Adversarial Model Perturbation", CVPR2021☆40Updated 4 years ago
- [NeurIPS 2020] "Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?" by Shen Yan, Yu Zheng, Wei Ao, X…☆50Updated 4 years ago
- Code for our ICLR'2021 paper "DrNAS: Dirichlet Neural Architecture Search"☆43Updated 4 years ago
- [NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)☆180Updated 4 years ago
- Official PyTorch implementation of “Flexible Dataset Distillation: Learn Labels Instead of Images”☆41Updated 5 years ago
- Smooth Adversarial Training☆68Updated 5 years ago
- Codes for Understanding Architectures Learnt by Cell-based Neural Architecture Search☆28Updated 5 years ago
- Official implementation of Auxiliary Learning by Implicit Differentiation [ICLR 2021]☆86Updated last year
- This repository provides code for "On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness".☆46Updated 3 years ago
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆105Updated 5 years ago
- Soft Threshold Weight Reparameterization for Learnable Sparsity☆90Updated 2 years ago
- [TPAMI 2019] The implementation for "Direction Concentration Learning: Enhancing Congruency in Machine Learning"☆23Updated 5 years ago
- Project page for our paper: Interpreting Adversarially Trained Convolutional Neural Networks☆66Updated 6 years ago
- [ICLR 2022] "Sparsity Winning Twice: Better Robust Generalization from More Efficient Training" by Tianlong Chen*, Zhenyu Zhang*, Pengjun…☆40Updated 3 years ago
- Code for Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot☆42Updated 5 years ago
- Code for Which Tasks Should Be Learned Together in Multi-task Learning?☆99Updated 2 years ago
- Data-Free Network Quantization With Adversarial Knowledge Distillation PyTorch☆30Updated 4 years ago