English
Related papers

Related papers: Moser-Tardos Algorithm: Beyond Shearer's Bound

200 papers

One of the main strengths of online algorithms is their ability to adapt to arbitrary data sequences. This is especially important in nonparametric settings, where performance is measured against rich classes of comparator functions that…

Machine Learning · Computer Science 2020-11-03 Ilja Kuzborskij , Nicolò Cesa-Bianchi

We construct the first asymptotically good relaxed locally correctable codes with polylogarithmic query complexity, bringing the upper bound polynomially close to the lower bound of Gur and Lachish (SICOMP 2021). Our result follows from…

Computational Complexity · Computer Science 2024-04-02 Vinayak M. Kumar , Geoffrey Mon

Karger (STOC 1995) gave the first FPTAS for the network (un)reliability problem, setting in motion research over the next three decades that obtained increasingly faster running times, eventually leading to a $\tilde{O}(n^2)$-time algorithm…

Data Structures and Algorithms · Computer Science 2023-07-21 Ruoxu Cen , William He , Jason Li , Debmalya Panigrahi

We give an algorithmic local lemma by establishing a sufficient condition for the uniform random walk on a directed graph to reach a sink quickly. Our work is inspired by Moser's entropic method proof of the Lov\'{a}sz Local Lemma (LLL) for…

Combinatorics · Mathematics 2015-04-10 Dimitris Achlioptas , Fotis Iliopoulos

The aim of this note is twofold. On the one hand, we present a streamlined version of Molloy's new proof of the bound $\chi(G) \leq (1+o(1))\Delta(G)/\ln \Delta(G)$ for triangle-free graphs $G$, avoiding the technicalities of the entropy…

Combinatorics · Mathematics 2019-06-04 Anton Bernshteyn

We develop a discrete gauge-theoretic framework for superposition in large language models (LLMs) that replaces the single-global-dictionary premise with a sheaf-theoretic atlas of local semantic charts. Contexts are clustered into a…

Machine Learning · Computer Science 2026-03-17 Hossein Javidnia

This work provides a novel convergence analysis for stochastic optimization in terms of stopping times, addressing the practical reality that algorithms are often terminated adaptively based on observed progress. Unlike prior approaches,…

Optimization and Control · Mathematics 2025-07-17 Yasong Feng , Yifan Jiang , Tianyu Wang , Zhiliang Ying

We present a new approach for finding matchings in dense graphs by building on Szemer\'edi's celebrated Regularity Lemma. This allows us to obtain non-trivial albeit slight improvements over longstanding bounds for matchings in streaming…

Data Structures and Algorithms · Computer Science 2022-07-20 Sepehr Assadi , Soheil Behnezhad , Sanjeev Khanna , Huan Li

Lipschitz continuity of algorithms, introduced by Kumabe and Yoshida (FOCS'23), measures the stability of an algorithm against small input perturbations. Algorithms with small Lipschitz continuity are desirable, as they ensure reliable…

Data Structures and Algorithms · Computer Science 2025-07-01 Tatsuya Gima , Soh Kumabe , Yuichi Yoshida

Motivated by online advertisement and exchange settings, greedy randomized algorithms for the maximum matching problem have been studied, in which the algorithm makes (random) decisions that are essentially oblivious to the input graph. Any…

Data Structures and Algorithms · Computer Science 2013-07-12 T-H. Hubert Chan , Fei Chen , Xiaowei Wu , Zhichao Zhao

The follow the leader (FTL) algorithm, perhaps the simplest of all online learning algorithms, is known to perform well when the loss functions it is used on are convex and positively curved. In this paper we ask whether there are other…

Machine Learning · Computer Science 2017-02-13 Ruitong Huang , Tor Lattimore , András György , Csaba Szepesvári

During recent years the interest of optimization and machine learning communities in high-probability convergence of stochastic optimization methods has been growing. One of the main reasons for this is that high-probability complexity…

Kolla and Tulsiani [KT07,Kolla11} and Arora, Barak and Steurer [ABS10] introduced the technique of subspace enumeration, which gives approximation algorithms for graph problems such as unique games and small set expansion; the running time…

Data Structures and Algorithms · Computer Science 2012-12-11 Shayan Oveis Gharan , Luca Trevisan

We study the local convergence rate of stochastic first-order methods under a local $\alpha$-Polyak-Lojasiewicz ($\alpha$-PL) condition in a neighborhood of a target connected component $\mathcal{M}$ of the local minimizer set. The…

Optimization and Control · Mathematics 2026-02-24 Saeed Masiha , Saber Salehkaleybar , Niao He , Negar Kiyavash , Patrick Thiran

A common theme in many extremal problems in graph theory is the relation between local and global properties of graphs. One of the most celebrated results of this type is the Ruzsa-Szemer\'edi triangle removal lemma, which states that if a…

Combinatorics · Mathematics 2016-12-01 Lior Gishboliner , Asaf Shapira

Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDPs) under the generative model. However, much less is known about the constrained…

Machine Learning · Computer Science 2025-09-23 Yukuan Wei , Xudong Li , Lin F. Yang

We give a Markov chain based algorithm for sampling almost uniform solutions of constraint satisfaction problems (CSPs). Assuming a canonical setting for the Lov\'asz local lemma, where each constraint is violated by a small number of…

Data Structures and Algorithms · Computer Science 2021-04-13 Weiming Feng , Kun He , Yitong Yin

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

Machine Learning · Statistics 2020-12-25 Yunbei Xu , Assaf Zeevi

We define the problem of linear Contextual Stochastic Shortest Path (CSSP), where at the beginning of each episode, the learner observes an adversarially chosen context that determines the MDP through a fixed but unknown linear function.…

Machine Learning · Computer Science 2025-11-18 Dor Polikar , Alon Cohen

We study differentially private (DP) stochastic optimization (SO) with loss functions whose worst-case Lipschitz parameter over all data may be extremely large or infinite. To date, the vast majority of work on DP SO assumes that the loss…

Machine Learning · Computer Science 2024-10-01 Andrew Lowy , Meisam Razaviyayn