Evaluating Probabilistic Inference in Deep Learning: Beyond Marginal Predictions
Lists
Only you see this
Abstract
A fundamental challenge for any intelligent system is prediction: given some inputs, can you predict corresponding outcomes? Most work on supervised learning has focused on producing accurate marginal predictions for each input. However, we show that for a broad class of decision problems, accurate joint predictions are required to deliver good performance. In particular, we establish several results pertaining to combinatorial decision problems, sequential predictions, and multi-armed bandits to elucidate the essential role of joint predictive distributions. Our treatment of multi-armed bandits introduces an approximate Thompson sampling algorithm and analytic techniques that lead to a new kind of regret bound.
BibTeX
@misc{lu2021evaluating,
author = {Xiuyuan Lu and Ian Osband and Benjamin Van Roy and Zheng Wen},
title = {{Evaluating Probabilistic Inference in Deep Learning: Beyond Marginal Predictions}},
year = {2021},
eprint = {2107.09224},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2107.09224},
}