English
Related papers

Related papers: Rigorous Implications of the Low-Degree Heuristic

200 papers

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…

Although the standard formulations of prediction problems involve fully-observed and noiseless data drawn in an i.i.d. manner, many applications involve noisy and/or missing data, possibly involving dependence, as well. We study these…

Statistics Theory · Mathematics 2015-03-19 Po-Ling Loh , Martin J. Wainwright

This paper presents new deterministic and distributed low-diameter decomposition algorithms for weighted graphs. In particular, we show that if one can efficiently compute approximate distances in a parallel or a distributed setting, one…

Data Structures and Algorithms · Computer Science 2022-09-07 Václav Rozhoň , Michael Elkin , Christoph Grunau , Bernhard Haeupler

Can autoregressive large language models (LLMs) learn consistent probability distributions when trained on sequences in different token orders? We prove formally that for any well-defined probability distribution, sequence perplexity is…

Computation and Language · Computer Science 2025-05-14 Xiaoliang Luo , Xinyi Xu , Michael Ramscar , Bradley C. Love

In this set of three companion manuscripts/articles, we unveil our new results on primality testing and reveal new primality testing algorithms enabled by those results. The results have been classified (and referred to) as…

Cryptography and Security · Computer Science 2019-08-21 Dhananjay Phatak , Alan T. Sherman , Steven D. Houston , Andrew Henry

In a distinguishing problem, the input is a sample drawn from one of two distributions and the algorithm is tasked with identifying the source distribution. The performance of a distinguishing algorithm is measured by its advantage, i.e.,…

Computational Complexity · Computer Science 2025-07-22 Ansh Nagda , Prasad Raghavendra

This paper proposes algorithms for learning two-level Boolean rules in Conjunctive Normal Form (CNF, i.e. AND-of-ORs) or Disjunctive Normal Form (DNF, i.e. OR-of-ANDs) as a type of human-interpretable classification model, aiming for a…

Machine Learning · Computer Science 2015-11-24 Guolong Su , Dennis Wei , Kush R. Varshney , Dmitry M. Malioutov

Random probabilities are a key component to many nonparametric methods in Statistics and Machine Learning. To quantify comparisons between different laws of random probabilities several works are starting to use the elegant Wasserstein over…

Statistics Theory · Mathematics 2024-05-27 Marta Catalano , Hugo Lavenant

We study two-layer belief networks of binary random variables in which the conditional probabilities Pr[childlparents] depend monotonically on weighted sums of the parents. In large networks where exact probabilistic inference is…

Machine Learning · Computer Science 2013-02-01 Michael Kearns , Lawrence Saul

The present study proposes incorporating non-parametric knowledge into the diffusion least-mean-squares algorithm in the framework of a maximum a posteriori (MAP) estimation. The proposed algorithm leads to a robust estimation of an unknown…

Machine Learning · Computer Science 2023-12-05 Soheil Ashkezari-Toussi , Hadi sadoghi-Yazdi

A new (unadjusted) Langevin Monte Carlo (LMC) algorithm with improved rates in total variation and in Wasserstein distance is presented. All these are obtained in the context of sampling from a target distribution $\pi$ that has a density…

Statistics Theory · Mathematics 2019-10-18 Sotirios Sabanis , Ying Zhang

We propose a distributionally robust approach to learning hyperparameters for first-order methods in convex optimization. Given a dataset of problem instances, we minimize a Wasserstein distributionally robust version of the performance…

Machine Learning · Computer Science 2026-05-08 Vinit Ranjan , Jisun Park , Bartolomeo Stellato

Leveraging algorithmic stability to derive sharp generalization bounds is a classic and powerful approach in learning theory. Since Vapnik and Chervonenkis [1974] first formalized the idea for analyzing SVMs, it has been utilized to study…

Machine Learning · Computer Science 2021-01-26 Qinghua Liu , Zhou Lu

Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. However, we find that deterministic evaluations fail to capture…

Machine Learning · Computer Science 2025-03-04 Yan Scholten , Stephan Günnemann , Leo Schwinn

We study the {\em robust proper learning} of univariate log-concave distributions (over continuous and discrete domains). Given a set of samples drawn from an unknown target distribution, we want to compute a log-concave hypothesis…

Data Structures and Algorithms · Computer Science 2016-06-10 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart

Real-world decision-making, from tax compliance assessment to medical diagnosis, requires aggregating multiple noisy and potentially contradictory evidence sources. Existing approaches either lack explicit uncertainty quantification (neural…

Artificial Intelligence · Computer Science 2026-03-19 Aliyu Agboola Alege

Capturing aleatoric uncertainty is a critical part of many machine learning systems. In deep learning, a common approach to this end is to train a neural network to estimate the parameters of a heteroscedastic Gaussian distribution by…

Machine Learning · Computer Science 2022-04-04 Maximilian Seitzer , Arash Tavakoli , Dimitrije Antic , Georg Martius

Let $\mathcal{L}$ be a language that can be decided in linear space and let $\epsilon >0$ be any constant. Let $\mathcal{A}$ be the exponential hardness assumption that for every $n$, membership in $\mathcal{L}$ for inputs of length~$n$…

Computational Complexity · Computer Science 2023-03-30 Edward Pyne , Ran Raz , Wei Zhan

Reliability of machine learning evaluation -- the consistency of observed evaluation scores across replicated model training runs -- is affected by several sources of nondeterminism which can be regarded as measurement noise. Current…

Machine Learning · Computer Science 2023-10-10 Michael Hagmann , Philipp Meier , Stefan Riezler

We develop a principled way of identifying probability distributions whose independent and identically distributed (iid) realizations are compressible, i.e., can be well-approximated as sparse. We focus on Gaussian random underdetermined…

Statistics Theory · Mathematics 2012-04-27 Rémi Gribonval , Volkan Cevher , Mike E. Davies
‹ Prev 1 3 4 5 6 7 10 Next ›