[IDA ML Seminar] DA Machine Learning Seminar 24/3 - Tom Rainforth

[Fredrik Lindsten]

Welcome to the IDA Machine Learning Seminar on Wednesday, March 24, 
15:15

Tom Rainforth, University of Oxford, UK
http://csml.stats.ox.ac.uk/people/rainforth/

Target Aware Bayesian Inference: How to Beat Optimal Conventional 
Estimators
Abstract: Standard approaches for Bayesian inference focus solely on 
approximating the posterior distribution. Typically, this approximation 
is, in turn, used to calculate expectations for one or more target 
functions--a computational pipeline that is inefficient when the target 
function(s) are known upfront. We address this inefficiency by 
introducing a framework for target-aware Bayesian inference (TABI) that 
estimates these expectations directly. While conventional Monte Carlo 
estimators have a fundamental limit on the error they can achieve for a 
given sample size, our TABI framework is able to breach this limit; it 
can theoretically produce arbitrarily accurate estimators using only 
three samples, while we show empirically that it can also breach this 
limit in practice. We utilize our TABI framework by combining it with 
adaptive importance sampling approaches and show both theoretically and 
empirically that the resulting estimators are capable of converging 
faster than the standard O(1/N) Monte Carlo rate, potentially producing 
rates as fast as O(1/N^2). We further combine our TABI framework with 
amortized inference methods, to produce a method for amortizing the cost 
of calculating expectations. Finally, we show how TABI can be used to 
convert any marginal likelihood estimator into a target aware inference 
scheme and demonstrate the substantial benefits this can yield.

Based on the paper of the same name by Rainforth, Golinski, Wood, and 
Zaidi, published in the Journal of Machine Learning Research 2020 and 
"Amortized Monte Carlo Integration" by Golinski, Wood, and Rainforth, 
ICML 2019 (Best Paper Honorable Mention).

Zoom link: 
https://liu-se.zoom.us/j/65907932927?pwd=Mld2c2Q4MFh4OU5LVStPUXBDSU43QT09
Meeting ID: 659 0793 2927
Passcode: 829609

-------
The list of future seminars in the series is available at 
http://www.ida.liu.se/research/machinelearning/seminars/.

Welcome!​
IDA Machine Learning Group
-------------- next part --------------
En HTML-bilaga skiljdes ut...
URL: <http://lists.liu.se/pipermail/ml-seminars/attachments/20210317/bad36ca4/attachment.html>