leventsagun / hessian-for-basicDL
can calculate the Hessian matrix and/or its spectrum for simple neural nets
☆10Updated 6 years ago
Alternatives and similar repositories for hessian-for-basicDL:
Users that are interested in hessian-for-basicDL are comparing it to the libraries listed below
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 5 years ago
- Code for the signSGD paper☆83Updated 4 years ago
- ☆27Updated 2 years ago
- This repo contains the code for the experiments in "Rademacher Complexity for Adversarially Robust Generalization"☆9Updated 5 years ago
- Implementation of SVRG and SAGA optimization algorithms for deep learning topics.☆73Updated 4 years ago
- ☆13Updated 6 years ago
- Implementation of Minimax Pareto Fairness framework☆21Updated 4 years ago
- R-GAP: Recursive Gradient Attack on Privacy [Accepted at ICLR 2021]☆36Updated 2 years ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆17Updated 5 years ago
- Official implementation for Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds (NeurIPS, 2021).☆23Updated 2 years ago
- Implementation of the paper "Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory", Ron Amit and Ron Meir, ICML 2018☆18Updated 4 years ago
- PyTorch Implementation of Federated Reconstruction: Partially Local Federated Learning☆13Updated 2 years ago
- Distributional and Outlier Robust Optimization (ICML 2021)☆26Updated 3 years ago
- Code for testing DCT plus Sparse (DCTpS) networks☆14Updated 3 years ago
- An (imperfect) implementation of wide resnets and Parseval regularization☆9Updated 5 years ago
- Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks☆13Updated 3 years ago
- Code for Global Convergence of Block Coordinate Descent in Deep Learning (ICML 2019)☆37Updated 5 years ago
- SGD with compressed gradients and error-feedback: https://arxiv.org/abs/1901.09847☆30Updated 9 months ago
- Learning rate adaptation for differentially private stochastic gradient descent☆16Updated 4 years ago
- Code for "Federated Accelerated Stochastic Gradient Descent" (NeurIPS 2020)☆15Updated 3 years ago
- Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network☆62Updated 5 years ago
- Official code for FAccT'21 paper "Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning" https://arxiv.org/abs…☆13Updated 4 years ago
- Tilted Empirical Risk Minimization (ICLR '21)☆59Updated last year
- The code for the paper: https://arxiv.org/abs/1806.06317☆24Updated 5 years ago
- Federated Principal Component Analysis Revisited!☆42Updated 3 years ago
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 4 years ago
- ☆42Updated 6 years ago
- SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning☆23Updated 6 years ago
- PyTorch implementation of efficient algorithms for DRO with CVaR and Chi-Square uncertainty sets☆59Updated 2 years ago
- Zeroth-order Min-max Optimization☆11Updated 4 years ago