Wu Lin

No description provided.

Code for ICLR 2026 paper on "Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization"

Code for ICML 2019 paper on "Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations"

Code for ICML 2020 paper on “Handling the Positive-Definite Constraint in the Bayesian Learning Rule”

Square-root-free Adaptive Methods; Experiment code for ICML 2024 paper on Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective

GPU- and TPU-backed NumPy with differentiation and JIT compilation.

A repo based on XiLin Li's PSGD repo that extends some of the experiments.

Matrix-multiplication-only KFAC; Code for ICML 2023 paper on Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning

Pytorch implementation of KFAC and E-KFAC (Natural Gradient).

No description provided.

Fast and Easy Infinite Neural Networks in Python

code for Structured Variational Autoencoders

No description provided.

code for the paper "Stein Variational Gradient Descent (SVGD): A General Purpose Bayesian Inference Algorithm"

Source-to-Source Debuggable Derivatives in Pure Python

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

some tools for gaussian linear dynamical systems

Source code for Naesseth et. al. "Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms" (2017)

Optimization functions for Julia

Accompanying source code for Machine Learning with TensorFlow. Refer to the book for step-by-step explanations.

Efficiently computes derivatives of numpy code.

No description provided.

No description provided.

Reimplementation of DRAW

TensorFlow implementation of Neural Variational Inference for Text Processing

Implementation in C and Theano of the method Probabilistic Backpropagation for scalable Bayesian inference in deep neural networks.

code for the paper "Improved Techniques for Training GANs"

Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autoregressive Flow"

Flexible Bayesian inference using TensorFlow

Code for my paper "Fixed-Form Variational Posterior Approximation through Stochastic Linear Regression"