team-approx-bayes / bayesian-sam
Code for "SAM as an Optimal Relaxation of Bayes", ICLR 2023.
☆21Updated last year
Related projects: ⓘ
- Improving Transformation Invariance in Contrastive Representation Learning☆13Updated 3 years ago
- ☆13Updated last year
- ☆40Updated last year
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆40Updated last year
- ☆34Updated last month
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆39Updated 10 months ago
- Supporing code for the paper "Bayesian Model Selection, the Marginal Likelihood, and Generalization".☆34Updated 2 years ago
- Code for Accelerated Linearized Laplace Approximation for Bayesian Deep Learning (ELLA, NeurIPS 22')☆16Updated last year
- ☆29Updated 2 years ago
- ☆13Updated last year
- NeurIPS 2021, Code for Measuring Generalization with Optimal Transport☆28Updated 2 years ago
- ☆18Updated 2 years ago
- Energy-Based Models for Continual Learning Official Repository (PyTorch)☆40Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆42Updated last year
- Code to implement the AND-mask and geometric mean to do gradient based optimization, from the paper "Learning explanations that are hard …☆39Updated 3 years ago
- Official PyTorch implementation of "Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error"☆30Updated last year
- This repository contains the code for our paper "Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguo…☆36Updated last year
- SGD with large step sizes learns sparse features [ICML 2023]☆31Updated last year
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆34Updated last year
- ☆17Updated last year
- Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness☆41Updated 3 years ago
- ☆23Updated 3 years ago
- ☆19Updated 4 years ago
- Code for ICLR 2022 Paper, "Controlling Directions Orthogonal to a Classifier"☆34Updated last year
- An Empirical Study of Invariant Risk Minimization☆28Updated 4 years ago
- Code for paper "Adversarial Support Alignment"☆21Updated 2 years ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆34Updated 2 years ago
- Official implementation of ORCA proposed in the paper "Cross-Modal Fine-Tuning: Align then Refine"☆63Updated 6 months ago
- Project for the Large Scale Optimization course at Skoltech☆22Updated 5 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 2 years ago