umutsimsekli / sgd_tail_index
The codebase for the paper "A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks"
☆21Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for sgd_tail_index
- A variational inference method with accurate uncertainty estimation. It uses a new semi-implicit variational family built on neural netwo…☆53Updated 3 weeks ago
- ☆57Updated last year
- Code for the paper Gaussian process behaviour in wide deep networks☆48Updated 6 years ago
- Implementation of the Functional Neural Process models☆43Updated 4 years ago
- Sample code for running deterministic variational inference to train Bayesian neural networks☆100Updated 6 years ago
- ☆66Updated 5 years ago
- ☆36Updated 3 years ago
- Code for "Training Deep Energy-Based Models with f-Divergence Minimization" ICML 2020☆35Updated last year
- Code for "A Spectral Approach to Gradient Estimation for Implicit Distributions" (ICML'18)☆32Updated last year
- Experiments for the paper "Exponential expressivity in deep neural networks through transient chaos"☆69Updated 8 years ago
- ☆87Updated 2 years ago
- Approximate Inference Turns Deep Networks into Gaussian Processes (dnn2gp)☆48Updated 4 years ago
- PyTorch implementation of Stein Variational Gradient Descent☆41Updated last year
- Scalable Training of Inference Networks for Gaussian-Process Models, ICML 2019☆41Updated last year
- Hypergradient descent☆138Updated 5 months ago
- ☆52Updated 3 months ago
- Code for "Functional variational Bayesian neural networks" (https://arxiv.org/abs/1903.05779)☆80Updated 4 years ago
- Convolutional Neural Tangent Kernel☆107Updated 5 years ago
- Stochastic algorithms for computing Regularized Optimal Transport☆55Updated 6 years ago
- demonstration of the information bottleneck theory for deep learning☆59Updated 7 years ago
- Official Release of "Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling"☆45Updated 4 years ago
- Path-SGD: Path-Normalized Optimization in Deep Neural Networks☆19Updated 5 years ago
- Natural Gradient, Variational Inference☆28Updated 4 years ago
- Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088☆53Updated 5 years ago
- Code to accompany paper 'Bayesian Deep Ensembles via the Neural Tangent Kernel'☆26Updated 3 years ago
- NTK reading group☆85Updated 4 years ago
- Computing various norms/measures on over-parametrized neural networks☆49Updated 5 years ago
- A tensorflow implementation of the NIPS 2018 paper "Variational Inference with Tail-adaptive f-Divergence"☆20Updated 5 years ago
- PyTorch implementation of Bidirectional Monte Carlo, Annealed Importance Sampling, and Hamiltonian Monte Carlo.☆52Updated 3 years ago