yiboyang / wgd
Official project page for Estimating the Rate-Distortion Function by Wasserstein Gradient Descent
☆17Updated last year
Alternatives and similar repositories for wgd:
Users that are interested in wgd are comparing it to the libraries listed below
- Code for Neural Estimation of the Rate-Distortion Function With Applications to Operational Source Coding☆12Updated last year
- Lossless compression using Probabilistic Circuits☆16Updated 3 years ago
- Kernel Stein Discrepancy Descent : a method to sample from unnormalized densities☆22Updated last year
- Featurized Density Ratio Estimation☆20Updated 3 years ago
- Official repo for the ICLR22 paper "Towards Empirical Sandwich Bounds on the Rate-Distortion Function"☆10Updated 2 years ago
- Demos for the paper Generalized Variational Inference (Knoblauch, Jewson & Damoulas, 2019)☆20Updated 6 years ago
- Code of the paper "Beyond calibration: estimating the grouping loss of modern neural networks" published in ICLR 2023.☆12Updated last year
- Improving ALISTA with neural augmentation☆15Updated 4 years ago
- ☆16Updated 7 months ago
- ☆17Updated 2 years ago
- Difference-of-Entropies (DoE) Estimator☆25Updated 3 years ago
- ☆12Updated 4 years ago
- Data compression in JAX☆64Updated 5 months ago
- ☆14Updated last year
- Mutual information estimators and benchmark☆48Updated 3 months ago
- Implementation of the transformer proposed in "Building Blocks for a Complex-Valued Transformer Architecture"☆73Updated last year
- Estimation of mutual information (MI) distribution with Gaussian mixture models (GMMs)☆18Updated 3 weeks ago
- [ICLR 2019] "ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA", by Jialin Liu*, Xiaohan Chen*, Zhangyang Wang and Wotao Y…☆70Updated 3 years ago
- Code for the paper "Let’s Make Block Coordinate Descent Go Fast"☆48Updated last year
- ☆19Updated 5 years ago
- ☆46Updated 2 weeks ago
- Adaptive gradient descent without descent☆47Updated 3 years ago
- Carpet: Neural Net based solver for the 1d-TV problem☆12Updated 4 years ago
- Code for 'Periodic Activation Functions Induce Stationarity' (NeurIPS 2021)☆18Updated 3 years ago
- Fast hyperparameter settings for non-smooth estimators:☆40Updated last year
- This is the official implementation of the ICML 2023 paper - Can Forward Gradient Match Backpropagation ?☆12Updated last year
- ☆39Updated 5 years ago
- LaTeX source code for the slides☆23Updated 3 years ago
- Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100☆18Updated 3 years ago
- Spectral Tensor Train Parameterization of Deep Learning Layers☆15Updated 3 years ago