Tom Rainforth

Publications
Influence

Tom Rainforth, F. Wood
Mathematics, Computer Science
ArXiv
20 July 2015

We introduce canonical correlation forests (CCFs), a new tree ensemble method for classification where the individual canonical correlation trees (CCTs) use hyperplane splits based on the feature projections from a canonical correlation analysis. Expand

Auto-Encoding Sequential Monte Carlo

T. Le, M. Igl, Tom Rainforth, T. Jin, Frank Wood
Computer Science, Mathematics
ICLR
29 May 2017

We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models. Expand

Tighter Variational Bounds are Not Necessarily Better

Tom Rainforth, Adam R. Kosiorek, +4 authors Y. Teh
Computer Science, Mathematics
ICML
13 February 2018

We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient estimator. Expand

Disentangling Disentanglement in Variational Autoencoders

Emile Mathieu, Tom Rainforth, Siddharth Narayanaswamy, Y. Teh
Computer Science, Mathematics
ICML
6 December 2018

We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the aggregate encoding of data conforming to a desired structure, represented through the prior. Expand

Interacting Particle Markov Chain Monte Carlo

Tom Rainforth, C. A. Naesseth, +4 authors F. Wood
Computer Science, Mathematics
ICML
16 February 2016

We introduce interacting particle Markov chain Monte Carlo (iPMCMC), a PMCMC method based on an interacting pool of standard and conditional sequential Monte Carlo samplers. Expand

On the Fairness of Disentangled Representations

Francesco Locatello, Gabriele Abbati, Tom Rainforth, S. Bauer, B. Schölkopf, Olivier Bachem
Computer Science, Mathematics
NeurIPS
31 May 2019

In this paper, we investigate the usefulness of different notions of disentanglement for improving the fairness of downstream prediction tasks based on representations. Expand

On Nesting Monte Carlo Estimators

Tom Rainforth, Robert Cornish, H. Yang, A. Warrington
Computer Science, Mathematics
ICML
18 September 2017

We investigate the statistical implications of nesting MC estimators, including cases of multiple levels of nesting, and establish the conditions under which they converge. Expand

A Statistical Approach to Assessing Neural Network Robustness

Stefan Webb, Tom Rainforth, Y. Teh, M. Kumar
Computer Science, Mathematics
ICLR
27 September 2018

We present a new approach to assessing the robustness of neural networks based on estimating the proportion of inputs for which a property is violated under an input model. Expand

Nesting Probabilistic Programs

Tom Rainforth
Computer Science, Mathematics
UAI
16 March 2018

We formalize the notion of nesting probabilistic programming queries and investigate the resulting statistical implications. Expand

Variational Bayesian Optimal Experimental Design

A. Foster, M. Jankowiak, +4 authors N. Goodman
Computer Science
NeurIPS
13 March 2019

We propose a variational BOED approach that sidesteps the double intractability of the EIG in a principled manner and yields estimators with convergence rates in line with those for conventional estimation problems. Expand

Recommended Authors