output
20122026
most citedCaptum: A unified and generic model interpretability library for PyTorch

649 citations

Showing 2021 · cs.LGShow all

38 papers · 2 filters

cs.LG2021★ 1 cited

Neural Pseudo-Label Optimism for the Bank Loan Problem

Aldo Pacchiano, Shaun Singh, Edward Chou +2

We study a class of classification problems best exemplified by the \emph{bank loan} problem, where a lender decides whether or not to issue a loan. The lender only observes whethe…

cs.LG2021

Information-Theoretic Bayes Risk Lower Bounds for Realizable Models

Matthew Nokleby, Ahmad Beirami

We derive information-theoretic lower bounds on the Bayes risk and generalization error of realizable machine learning models. In particular, we employ an analysis in which the rat…

cs.LG2021★ 7 cited

Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning

Qinkai Zheng, Xu Zou, Yuxiao Dong +5

Adversarial attacks on graphs have posed a major threat to the robustness of graph machine learning (GML) models. Naturally, there is an ever-escalating arms race between attackers…

cs.LG2021

Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters

Takanori Maehara, Hoang NT

Theoretical analyses for graph learning methods often assume a complete observation of the input graph. Such an assumption might not be useful for handling any-size graphs due to t…

cs.LG2021★ 26 cited

Learning in High Dimension Always Amounts to Extrapolation

Randall Balestriero, Jerome Pesenti, Yann LeCun

The notion of interpolation and extrapolation is fundamental in various fields from deep learning to function approximation. Interpolation occurs for a sample whenever this sam…

cs.LG2021★ 2 cited

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection

Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano +3

We study the role of the representation of state-action value functions in regret minimization in finite-horizon Markov Decision Processes (MDPs) with linear structure. We first de…