activity
20122023
most citedFinito: A Faster, Permutable Incremental Gradient Method for Big Data Problems

72 citations · 78 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG2023

Sample Average Approximation for Black-Box VI

Javier Burroni, Justin Domke, Daniel Sheldon

We present a novel approach for black-box VI that bypasses the difficulties of stochastic gradient ascent, including the task of selecting step-sizes. Our approach involves using a…

cs.LG2023

U-Statistics for Importance-Weighted Variational Inference

Javier Burroni, Kenta Takatsu, Justin Domke +1

We propose the use of U-statistics to reduce variance for gradient estimation in importance-weighted variational inference. The key observation is that, given a base gradient estim…

cs.LG20143 cited

Projecting Markov Random Field Parameters for Fast Mixing

Xianghang Liu, Justin Domke

Markov chain Monte Carlo (MCMC) algorithms are simple and extremely powerful techniques to sample from almost arbitrary distributions. The flaw in practice is that it can take a la…

cs.LG201472 cited

Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems

Aaron J. Defazio, Tibério S. Caetano, Justin Domke

Recent advances in optimization theory have shown that smooth strongly convex finite sums can be minimized faster than by treating them as a black box "batch" problem. In this work…

cs.LG20141 cited

Structured Learning via Logistic Regression

Justin Domke

A successful approach to structured learning is to write the learning objective as a joint function of linear parameters and inference messages, and iterate between updates to each…

cs.LG2014

Projecting Ising Model Parameters for Fast Mixing

Justin Domke, Xianghang Liu

Inference in general Ising models is difficult, due to high treewidth making tree-based algorithms intractable. Moreover, when interactions are strong, Gibbs sampling may take expo…