uuujf / SGDNoiseLinks
[ICML 2019] The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
☆14Updated 5 years ago
Alternatives and similar repositories for SGDNoise
Users that are interested in SGDNoise are comparing it to the libraries listed below
Sorting:
- Pytorch implementation of neural processes and variants☆29Updated last year
- ☆68Updated 6 years ago
- Official implementation of Transformer Neural Processes☆78Updated 3 years ago
- Pytorch Implementation of the Nonlinear Information Bottleneck☆41Updated last year
- Experiments from the paper "On Second Order Behaviour in Augmented Neural ODEs"☆61Updated last year
- Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness☆48Updated 4 years ago
- Refining continuous-in-depth neural networks☆42Updated 4 years ago
- [ICLR 2022] "Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How" by Yuning You, Yue Cao, Tianl…☆14Updated 3 years ago
- Official code for the ICLR 2021 paper Neural ODE Processes☆75Updated 3 years ago
- Code for Knowledge-Adaptation Priors based on the NeurIPS 2021 paper by Khan and Swaroop.☆16Updated 3 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆19Updated 6 years ago
- Code for Accelerated Linearized Laplace Approximation for Bayesian Deep Learning (ELLA, NeurIPS 22')☆16Updated 3 years ago
- ☆13Updated 4 years ago
- ☆50Updated 2 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆106Updated 5 years ago
- Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).☆58Updated 5 years ago
- Example code of Sparse Gaussian Process Attention (ICLR 2023)☆26Updated 3 months ago
- ☆73Updated last year
- Code to accompany paper 'Bayesian Deep Ensembles via the Neural Tangent Kernel'☆26Updated 4 years ago
- Contains code for the NeurIPS 2020 paper by Pan et al., "Continual Deep Learning by FunctionalRegularisation of Memorable Past"☆44Updated 5 years ago
- NeurIPS'22 Oral: EquiVSet - Learning Neural Set Functions Under the Optimal Subset Oracle☆21Updated 3 years ago
- ☆28Updated 2 years ago
- [ICML 2021] This is the official github repo for training L_inf dist nets with high certified accuracy.☆42Updated 3 years ago
- Neural Tangent Kernel Papers☆120Updated 11 months ago
- Supporing code for the paper "Bayesian Model Selection, the Marginal Likelihood, and Generalization".☆37Updated 3 years ago
- Code for A General Recipe for Likelihood-free Bayesian Optimization, ICML 2022☆46Updated 3 years ago
- Approximate Inference Turns Deep Networks into Gaussian Processes (dnn2gp)☆48Updated 6 years ago
- GflowNets, MCMC, Metropolis-Hasting, Gibbs sampling, Metropolis-adjusted Langevin, Inverse Transform Sampling, Acceptance-Rejection Metho…☆86Updated 2 years ago
- [ICML'21] Improved Contrastive Divergence Training of Energy Based Models☆69Updated 3 years ago
- Deep Learning & Information Bottleneck☆63Updated 2 years ago