parthnatekar / pgdl
Winning Solution of the NeurIPS 2020 Competition on Predicting Generalization in Deep Learning
☆40Updated 4 years ago
Alternatives and similar repositories for pgdl:
Users that are interested in pgdl are comparing it to the libraries listed below
- Computing various measures and generalization bounds on convolutional and fully connected networks☆35Updated 6 years ago
- NeurIPS 2021, Code for Measuring Generalization with Optimal Transport☆28Updated 3 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆61Updated 4 years ago
- A Closer Look at Accuracy vs. Robustness☆88Updated 3 years ago
- [NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features☆56Updated 2 years ago
- Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness☆44Updated 4 years ago
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 4 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- ☆55Updated 4 years ago
- ☆58Updated 2 years ago
- ☆44Updated 4 years ago
- Last-layer Laplace approximation code examples☆83Updated 3 years ago
- ☆20Updated 4 years ago
- Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)☆28Updated 4 years ago
- ICLR 2021, Fair Mixup: Fairness via Interpolation☆56Updated 3 years ago
- ☆35Updated last year
- ☆19Updated 4 years ago
- Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization☆86Updated 2 years ago
- Training vision models with full-batch gradient descent and regularization☆37Updated 2 years ago
- ☆38Updated 3 years ago
- ☆40Updated 5 years ago
- ☆107Updated last year
- Code to accompany paper 'Bayesian Deep Ensembles via the Neural Tangent Kernel'☆26Updated 4 years ago
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆41Updated 2 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆71Updated 11 months ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Updated 4 years ago
- Code to implement the AND-mask and geometric mean to do gradient based optimization, from the paper "Learning explanations that are hard …☆39Updated 4 years ago
- ☆64Updated 4 years ago
- ☆34Updated 4 years ago
- ☆34Updated 3 years ago