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
- Code for the signSGD paper☆82Updated 4 years ago
- Code for "Federated Accelerated Stochastic Gradient Descent" (NeurIPS 2020)☆15Updated 3 years ago
- Implementation of SVRG and SAGA optimization algorithms for deep learning topics.☆70Updated 4 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 5 years ago
- This repo contains the code for the experiments in "Rademacher Complexity for Adversarially Robust Generalization"☆9Updated 5 years ago
- ☆27Updated 2 years ago
- SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning☆23Updated 6 years ago
- Federated posterior averaging implemented in JAX☆51Updated last year
- Code for testing DCT plus Sparse (DCTpS) networks☆14Updated 3 years ago
- Federated Principal Component Analysis Revisited!☆39Updated 3 years ago
- vector quantization for stochastic gradient descent.☆33Updated 4 years ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆17Updated 5 years ago
- PyTorch Implementation of Federated Reconstruction: Partially Local Federated Learning☆12Updated 2 years ago
- Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks☆13Updated 2 years ago
- Implementation of Minimax Pareto Fairness framework☆21Updated 4 years ago
- CIFAR-5m dataset☆38Updated 4 years ago
- Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network☆63Updated 5 years ago
- Code for Global Convergence of Block Coordinate Descent in Deep Learning (ICML 2019)☆35Updated 5 years ago
- SGD with compressed gradients and error-feedback: https://arxiv.org/abs/1901.09847☆31Updated 6 months ago
- ☆13Updated 6 years ago
- The code for the paper: https://arxiv.org/abs/1806.06317☆24Updated 5 years ago
- Computing various norms/measures on over-parametrized neural networks☆49Updated 6 years ago
- Decentralized SGD and Consensus with Communication Compression: https://arxiv.org/abs/1907.09356☆66Updated 4 years ago
- CoLa - Decentralized Linear Learning: https://arxiv.org/abs/1808.04883☆20Updated 3 years ago
- ☆18Updated 2 years ago
- PyTorch implementation of efficient algorithms for DRO with CVaR and Chi-Square uncertainty sets☆58Updated 2 years ago
- PyTorch reimplementation of computing Shapley values via Truncated Monte Carlo sampling from "What is your data worth? Equitable Valuatio…☆25Updated 3 years ago
- Salvaging Federated Learning by Local Adaptation☆56Updated 6 months ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆52Updated 4 years ago
- Code for the paper "MMA Training: Direct Input Space Margin Maximization through Adversarial Training"☆34Updated 4 years ago