kilianFatras / variance_reduced_neural_networks
Implementation of SVRG and SAGA optimization algorithms for deep learning topics.
☆69Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for variance_reduced_neural_networks
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 3 years ago
- Tilted Empirical Risk Minimization (ICLR '21)☆59Updated last year
- Code for Global Convergence of Block Coordinate Descent in Deep Learning (ICML 2019)☆34Updated 5 years ago
- ☆57Updated last year
- ZOSVRG-BlackBox-Adv☆11Updated 6 years ago
- Code for the paper "Understanding Generalization through Visualizations"☆60Updated 3 years ago
- can calculate the Hessian matrix and/or its spectrum for simple neural nets☆10Updated 6 years ago
- Implementation of an efficient variant of SVRG that relies on mini-batching implemented in Pytorch☆26Updated 5 years ago
- Attempt to speed Randomized SVD(Singular Value Decomposition) Using pytorch and it's gnu capabilities.☆17Updated 6 years ago
- PyTorch implementation of FIM and empirical FIM☆58Updated 6 years ago
- Code for the paper "MMA Training: Direct Input Space Margin Maximization through Adversarial Training"☆34Updated 4 years ago
- ☆82Updated 4 years ago
- ☆67Updated 5 years ago
- Limitations of the Empirical Fisher Approximation☆45Updated 4 years ago
- Certifying Some Distributional Robustness with Principled Adversarial Training (https://arxiv.org/abs/1710.10571)☆45Updated 6 years ago
- demonstration of the information bottleneck theory for deep learning☆59Updated 7 years ago
- Distributional and Outlier Robust Optimization (ICML 2021)☆27Updated 3 years ago
- A Closer Look at Accuracy vs. Robustness☆88Updated 3 years ago
- Minimax Optimization, Stackelberg Games, Generative Adversarial Networks☆18Updated 4 years ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Updated 4 years ago
- Code for the signSGD paper☆81Updated 3 years ago
- ☆49Updated last year
- ☆19Updated 5 years ago
- Official implementation for Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds (NeurIPS, 2021).☆22Updated 2 years ago
- ☆74Updated 5 years ago
- [ICML 2019] ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation☆52Updated 2 months ago
- Example code for paper "Bilevel Optimization: Nonasymptotic Analysis and Faster Algorithms"☆43Updated 2 years ago
- The Search for Sparse, Robustness Neural Networks☆11Updated last year