SGD with large step sizes learns sparse features [ICML 2023]
☆33Apr 24, 2023Updated 2 years ago
Alternatives and similar repositories for sgd-sparse-features
Users that are interested in sgd-sparse-features are comparing it to the libraries listed below
Sorting:
- ☆38Jun 10, 2021Updated 4 years ago
- Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data☆13Sep 20, 2022Updated 3 years ago
- Official implementation of NeurIPS'24 Spotlight paper "Monte Carlo Tree Search based Space Transfer for Black-box Optimization".☆12Nov 28, 2024Updated last year
- Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks☆46Feb 24, 2022Updated 4 years ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆47Dec 8, 2022Updated 3 years ago
- Python package for the ICML 2022 paper "Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors".☆10Sep 2, 2024Updated last year
- On the effectiveness of adversarial training against common corruptions [UAI 2022]☆30May 16, 2022Updated 3 years ago
- Code related to ’Beyond spectral gap: The role of the topology in decentralized learning‘.☆13Jun 7, 2022Updated 3 years ago
- ☆15Dec 7, 2021Updated 4 years ago
- Every Call is Precious: Global Optimization of Black-Box Functions with Unknown Lipschitz Constants☆16Nov 30, 2025Updated 3 months ago
- ☆12Jul 25, 2024Updated last year
- Implemenation of PQMass from Lemos et al. 2024☆19Apr 23, 2025Updated 10 months ago
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Jan 10, 2023Updated 3 years ago
- A School for All Seasons on Trustworthy Machine Learning☆12Jun 30, 2021Updated 4 years ago
- Connecting Interpretability and Robustness in Decision Trees through Separation☆17May 8, 2021Updated 4 years ago
- Understanding and Improving Fast Adversarial Training [NeurIPS 2020]☆96Sep 23, 2021Updated 4 years ago
- RayS: A Ray Searching Method for Hard-label Adversarial Attack (KDD2020)☆57Nov 5, 2020Updated 5 years ago
- Source code for "Neural Anisotropy Directions"☆16Nov 17, 2020Updated 5 years ago
- Supervised Training of Conditional Monge Maps☆19Oct 30, 2023Updated 2 years ago
- Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]☆21Apr 15, 2024Updated last year
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆38Jun 14, 2022Updated 3 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Sep 11, 2023Updated 2 years ago
- [NeurIPS 2023] Code for the paper "Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threa…☆39Dec 3, 2024Updated last year
- A simple BLOSUM module for python3☆18Nov 21, 2025Updated 3 months ago
- Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.☆18May 31, 2023Updated 2 years ago
- Code for paper "Robustness of Bayesian Neural Networks to Gradient-Based Attacks"☆17Feb 26, 2024Updated 2 years ago
- Pytorch implementation of regularization methods for deep networks obtained via kernel methods.☆23Dec 27, 2019Updated 6 years ago
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Apr 28, 2024Updated last year
- Source code of "What can linearized neural networks actually say about generalization?☆20Oct 21, 2021Updated 4 years ago
- Implementation of Confidence-Calibrated Adversarial Training (CCAT).☆45Aug 3, 2020Updated 5 years ago
- Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"☆21Dec 10, 2021Updated 4 years ago
- Official Repository for ICML 2023 paper "Can Neural Network Memorization Be Localized?"☆21Oct 26, 2023Updated 2 years ago
- ☆23Jan 25, 2024Updated 2 years ago
- ☆42Dec 8, 2022Updated 3 years ago
- A community-run reference for state-of-the-art adversarial example defenses.☆52Oct 13, 2024Updated last year
- ☆30Jun 19, 2023Updated 2 years ago
- ICML 2019. Turn a pre-trained GAN model into a content-addressable model without retraining.☆21Jul 25, 2024Updated last year
- Official repo for the paper "Make Some Noise: Reliable and Efficient Single-Step Adversarial Training" (https://arxiv.org/abs/2202.01181)☆25Oct 17, 2022Updated 3 years ago
- Code for our ICLR19 paper "Wasserstein Barycenters for Model Ensembling", Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jarret Ross, Cicero…☆23Nov 18, 2019Updated 6 years ago