1k citations · 1.9k across the 49 of their papers we have counts for
6 papers · 1 filter
Learning Generalized Gumbel-max Causal Mechanisms
Guy Lorberbom, Daniel D. Johnson, Chris J. Maddison +2
To perform counterfactual reasoning in Structural Causal Models (SCMs), one needs to know the causal mechanisms, which provide factorizations of conditional distributions into nois…
Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts
Wouter Kool, Chris J. Maddison, Andriy Mnih
Training large-scale mixture of experts models efficiently on modern hardware requires assigning datapoints in a batch to different experts, each with a limited capacity. Recently…
Lossy Compression for Lossless Prediction
Yann Dubois, Benjamin Bloem-Reddy, Karen Ullrich +1
Most data is automatically collected and only ever "seen" by algorithms. Yet, data compressors preserve perceptual fidelity rather than just the information needed by algorithms pe…
Learning to Extend Program Graphs to Work-in-Progress Code
Xuechen Li, Chris J. Maddison, Daniel Tarlow
Source code spends most of its time in a broken or incomplete state during software development. This presents a challenge to machine learning for code, since high-performing model…
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…
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
Will Grathwohl, Kevin Swersky, Milad Hashemi +2
We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respec…