649 citations
- Carnegie Mellon UniversityUS26 papers
- Stanford UniversityUS20 papers
- Google (United States)US14 papers
- Georgia Institute of TechnologyUS13 papers
- Tel Aviv UniversityIL12 papers
- Cornell UniversityUS11 papers
- Meta (United States)US11 papers
- University of California, BerkeleyUS11 papers
- University College LondonGB10 papers
- Harvard University PressUS9 papers
- Johns Hopkins UniversityUS9 papers
- Massachusetts Institute of TechnologyUS9 papers
38 papers · 2 filters
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…
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…
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…
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…
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…
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…