samuelstanton / gnosisLinks
Code to reproduce experiments from 'Does Knowledge Distillation Really Work' a paper which appeared in the 2021 NeurIPS proceedings.
☆33Updated last year
Alternatives and similar repositories for gnosis
Users that are interested in gnosis are comparing it to the libraries listed below
Sorting:
- ☆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 2 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆61Updated 4 years ago
- [CVPR 2021] "The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models" Tianlong Chen, Jon…☆69Updated 2 years ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 3 years ago
- Last-layer Laplace approximation code examples☆82Updated 3 years ago
- [ICLR 2021 Spotlight Oral] "Undistillable: Making A Nasty Teacher That CANNOT teach students", Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Che…☆81Updated 3 years ago
- ☆23Updated 2 years ago
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 4 years ago
- The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from t…☆80Updated 3 years ago
- Computing various measures and generalization bounds on convolutional and fully connected networks☆35Updated 6 years ago
- Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxi…☆68Updated 3 years ago
- Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization☆87Updated 3 years ago
- Winning Solution of the NeurIPS 2020 Competition on Predicting Generalization in Deep Learning☆40Updated 4 years ago
- Offical Repo for Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks. Accepted by Neurips 2020.☆34Updated 4 years ago
- ICLR 2021, Fair Mixup: Fairness via Interpolation