English
Related papers

Related papers: Universality, optimality, and randomness deficienc…

200 papers

The current evaluation of mathematical skills in LLMs is limited, as existing benchmarks are either relatively small, primarily focus on elementary and high-school problems, or lack diversity in topics. Additionally, the inclusion of visual…

Computation and Language · Computer Science 2026-02-03 Konstantin Chernyshev , Vitaliy Polshkov , Ekaterina Artemova , Alex Myasnikov , Vlad Stepanov , Alexei Miasnikov , Sergei Tilga

Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models…

Computation and Language · Computer Science 2025-12-15 Zhewei Kang , Xuandong Zhao , Dawn Song

Identifying leading measurement units from a large collection is a common inference task in various domains of large-scale inference. Testing approaches, which measure evidence against a null hypothesis rather than effect magnitude, tend to…

Methodology · Statistics 2020-11-17 Nicholas C. Henderson , Michael A. Newton

We study the approximation properties of random ReLU features through their reproducing kernel Hilbert space (RKHS). We first prove a universality theorem for the RKHS induced by random features whose feature maps are of the form of nodes…

Machine Learning · Statistics 2019-08-19 Yitong Sun , Anna Gilbert , Ambuj Tewari

Modern challenges of robustness, fairness, and decision-making in machine learning have led to the formulation of multi-distribution learning (MDL) frameworks in which a predictor is optimized across multiple distributions. We study the…

Machine Learning · Computer Science 2024-12-19 Rajeev Verma , Volker Fischer , Eric Nalisnick

A real \alpha is called recursively enumerable ("r.e." for short) if there exists a computable, increasing sequence of rationals which converges to \alpha. It is known that the randomness of an r.e. real \alpha can be characterized in…

Computational Complexity · Computer Science 2015-05-13 Kohtaro Tadaki

We study algorithmic randomness notions via effective versions of almost-everywhere theorems from analysis and ergodic theory. The effectivization is in terms of objects described by a computably enumerable set, such as lower semicomputable…

Logic · Mathematics 2016-03-22 Kenshi Miyabe , André Nies , Jing Zhang

Recently, there has been remarkable progress in reinforcement learning (RL) with general function approximation. However, all these works only provide regret or sample complexity guarantees. It is still an open question if one can achieve…

Machine Learning · Computer Science 2023-05-16 Yue Wu , Jiafan He , Quanquan Gu

We derive a consistency result, in the $L_1$-sense, for incomplete U-statistics in the non-standard case where the kernel at hand has infinite second-order moments. Assuming that the kernel has finite moments of order $p(\geq 1)$, we obtain…

Statistics Theory · Mathematics 2021-12-30 Alexander Dürre , Davy Paindaveine

Based on the Delsarte-Yudin linear programming approach, we extend Levenshtein's framework to obtain lower bounds for the minimum $h$-energy of spherical codes of prescribed dimension and cardinality, and upper bounds on the maximal…

Metric Geometry · Mathematics 2022-10-19 Peter Boyvalenkov , Peter Dragnev , Douglas Hardin , Edward Saff , Maya Stoyanova

Machine learning (ML) methods are highly flexible, but their ability to approximate the true data-generating process is fundamentally constrained by finite samples. We characterize a universal lower bound, the Limits-to-Learning Gap (LLG),…

Machine Learning · Statistics 2025-12-16 Zhimin Chen , Bryan Kelly , Semyon Malamud

We establish fundamental mathematical limits on universal approximation theorem (UAT) system alignment by proving that catastrophic failures are an inescapable feature of any useful computational system. Our central thesis is that for any…

Machine Learning · Computer Science 2025-07-08 Jasper Yao

Embeddings play a pivotal role across various disciplines, offering compact representations of complex data structures. Randomized methods like Johnson-Lindenstrauss (JL) provide state-of-the-art and essentially unimprovable theoretical…

Machine Learning · Statistics 2024-12-11 Nikos Tsikouras , Constantine Caramanis , Christos Tzamos

The authors present evidence for universality in numerical computations with random data. Given a (possibly stochastic) numerical algorithm with random input data, the time (or number of iterations) to convergence (within a given tolerance)…

Numerical Analysis · Mathematics 2015-06-22 Percy Deift , Govind Menon , Sheehan Olver , Thomas Trogdon

Self-testing is a phenomenon where the use of specific quantum states or measurements can be inferred solely from the correlations they generate. We introduce a universal method for conducting robustness analysis in the self-testing of…

Quantum Physics · Physics 2026-03-23 Shin-Liang Chen , Nikolai Miklin

We consider the random lasing from a weakly scattering medium and demonstrate that the distribution of the threshold gain over the ensemble of statistically independent finite-size samples is universal. Universality stems from the facts…

Disordered Systems and Neural Networks · Physics 2009-11-10 V. M. Apalkov , M. E. Raikh

Majority voting over multiple LLM attempts improves mathematical reasoning, but correlated errors limit the effective sample size. A natural fix is to assign different reasoning strategies to different voters. The approach, Diverse Prompt…

Computation and Language · Computer Science 2026-04-17 Natapong Nitarach

We consider best approximation problems in a nonlinear subset $\mathcal{M}$ of a Banach space of functions $(\mathcal{V},\|\bullet\|)$. The norm is assumed to be a generalization of the $L^2$-norm for which only a weighted Monte Carlo…

Numerical Analysis · Mathematics 2021-05-13 Martin Eigel , Reinhold Schneider , Philipp Trunschke

We study the performance of classical and quantum machine learning (ML) models in predicting outcomes of physical experiments. The experiments depend on an input parameter $x$ and involve execution of a (possibly unknown) quantum process…

Quantum Physics · Physics 2021-05-19 Hsin-Yuan Huang , Richard Kueng , John Preskill

Recent studies have raised significant concerns regarding the reliability of current mathematics benchmarks, highlighting issues such as simplistic design and potential data contamination. Consequently, developing a reliable benchmark that…

Computation and Language · Computer Science 2025-08-14 Zijin Hong , Hao Wu , Su Dong , Junnan Dong , Yilin Xiao , Yujing Zhang , Zhu Wang , Feiran Huang , Linyi Li , Hongxia Yang , Xiao Huang