The paper resolves a key question in statistical learning under adversarial corruption by showing that sample‑adaptive and sample‑oblivious adversaries are equivalent up to polynomial factors in the sample size for all corruption types. It proves that any algorithm that succeeds against a sample‑oblivious adversary can be transformed into one that succeeds against the corresponding sample‑adaptive adversary by requesting a polynomially larger sample and running the original algorithm on a random subsample. The construction preserves computational efficiency and requires only a simple modification of the algorithm.
By Guy Blanc, Gregory Valiant
arXiv:2608. 06262v1 Announce Type: new Abstract: Model evaluations may fix all tests before observing any responses or select later tests using earlier responses.
By Zonghuan Xu
arXiv:2608. 02176v1 Announce Type: cross Abstract: We study the round complexity of learning a hidden partition $\mathcal{P}$ of an $n$-element universe using PAIR queries: PAIR($x,y$) tells us whether $x$ and $y$ belong to the same part of the partition or not.
By Deeparnab Chakrabarty, Aditi Dudeja, David Saulpic
arXiv:2607. 24732v1 Announce Type: cross Abstract: Motivated by learning from heterogeneous and overlapping data providers, we study a stylized model of distribution learning from restricted conditional samples.
By Jon Kleinberg, Amin Saberi, Xizhi Tan, Grigoris Velegkas
arXiv:2606. 11437v1 Announce Type: cross Abstract: Efficiently sampling from a complex probability distribution is a fundamental problem which has become increasingly pertinent in recent years with the rise of generative AI, as sophisticated sampling procedures from LLMs have been proposed to solve challenging reasoning problems.
By Noah Golowich, Ankur Moitra, Dhruv Rohatgi
arXiv:2603. 16798v2 Announce Type: replace Abstract: We study mean estimation for a Gaussian distribution with identity covariance in $\mathbb{R}^d$ under a missing data scheme termed realizable $\epsilon$-contamination model.
By Ilias Diakonikolas, Daniel M. Kane, Thanasis Pittas
arXiv:2604. 08438v2 Announce Type: replace Abstract: The Shapley value, and its broader family of semi-values, has received much attention in various attribution problems.
By Weida Li, Yaoliang Yu, Bryan Kian Hsiang Low
arXiv:2602. 03972v3 Announce Type: replace-cross Abstract: The best-arm identification (BAI) problem is one of the most fundamental problems in interactive machine learning, which has two flavors: the fixed-budget setting (FB) and the fixed-confidence setting (FC).
By Kapilan Balagopalan, Yinan Li, Yao Zhao, Tuan Nguyen, Anton Daitche, Houssam Nassif, Kwang-Sung Jun
arXiv:2607. 15528v1 Announce Type: new Abstract: Following Goldwasser, Rothblum, Shafer, and Yehudayoff, who defined a framework for interactive proofs of learning [ITCS'21], we initiate the study of non-interactive proofs of learning.
By Michael Ngo, Michael P. Kim
arXiv:2602. 16568v2 Announce Type: replace-cross Abstract: Sparse recovery is among the most well-studied problems in learning theory and high-dimensional statistics.
By Ziyun Chen, Jerry Li, Kevin Tian, Yusong Zhu
arXiv:2606. 25777v1 Announce Type: cross Abstract: We initiate a resource-aware theory of \textit{language generation in the limit} under the minimal constraint of space efficiency.
By Nicolas Flammarion, Chirag Pabbaraju, Hristo Papazov, Miltiadis Stouras, Ola Svensson
arXiv:2609. 13954v1 Announce Type: new Abstract: Ensemble sampling offers a practical approach to randomized exploration by maintaining a collection of models, but how small an ensemble can be while retaining strong regret guarantees remains unresolved.
By Taehyun Hwang, Min-hwan Oh