107 citations · 185 across the 13 of their papers we have counts for
5 papers · 1 filter
Adaptive Optimization with Examplewise Gradients
Julius Kunze, James Townsend, David Barber
We propose a new, more general approach to the design of stochastic gradient-based optimization methods for machine learning. In this new framework, optimizers assume access to a b…
Compressing Multisets with Large Alphabets using Bits-Back Coding
Daniel Severo, James Townsend, Ashish Khisti +2
Current methods which compress multisets at an optimal rate have computational complexity that scales linearly with alphabet size, making them too slow to be practical in many real…
Lossless Compression with Latent Variable Models
James Townsend
We develop a simple and elegant method for lossless compression using latent variable models, which we call 'bits back with asymmetric numeral systems' (BB-ANS). The method involve…
Lossless compression with state space models using bits back coding
James Townsend, Iain Murray
We generalize the 'bits back with ANS' method to time-series models with a latent Markov structure. This family of models includes hidden Markov models (HMMs), linear Gaussian stat…
Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
Yangjun Ruan, Karen Ullrich, Daniel Severo +5
Latent variable models have been successfully applied in lossless compression with the bits-back coding algorithm. However, bits-back suffers from an increase in the bitrate equal…