English
Related papers

Related papers: On Optimal Testing of Linearity

200 papers

Machine learning (ML) enables the development of interatomic potentials that promise the accuracy of first principles methods while retaining the low cost and parallel efficiency of empirical potentials. While ML potentials traditionally…

Scaling model parameters has become the de facto strategy for improving NLP systems, but it comes with substantial computational costs. Test-Time Scaling (TTS) offers an alternative by allocating more computation at inference: generating…

Computation and Language · Computer Science 2025-09-24 Shaomu Tan , Ryosuke Mitani , Ritvik Choudhary , Toshiyuki Sekiya

Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong…

Machine Learning · Computer Science 2023-05-23 Germano Gabbianelli , Gergely Neu , Nneka Okolo , Matteo Papini

We study the compute-optimal trade-off between model and training data set sizes for large neural networks. Our result suggests a linear relation similar to that supported by the empirical analysis of chinchilla. While that work studies…

Machine Learning · Computer Science 2023-10-20 Hong Jun Jeon , Benjamin Van Roy

Permutation tests are widely recognized as robust alternatives to tests based on normal theory. Random permutation tests have been frequently employed to assess the significance of variables in linear models. Despite their widespread use,…

Methodology · Statistics 2023-12-29 Leying Guan

Property testing is concerned with the design of algorithms making a sublinear number of queries to distinguish whether the input satisfies a given property or is far from having this property. A seminal paper of Alon, Krivelevich, Newman,…

Data Structures and Algorithms · Computer Science 2025-04-29 Gabriel Bathie , Nathanaël Fijalkow , Corto Mascle

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Qiyang Li , Sergey Levine

This work is concerned with the estimation of multidimensional regression and the asymptotic behaviour of the test involved in selecting models. The main problem with such models is that we need to know the covariance matrix of the noise to…

Statistics Theory · Mathematics 2008-02-20 Joseph Rynkiewicz

The goal of property testing is to quickly distinguish between objects which satisfy a property and objects that are $\epsilon$-far from satisfying the property. There are now several general results in this area which show that natural…

Combinatorics · Mathematics 2018-04-05 Jacob Fox , Fan Wei

Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world…

Artificial Intelligence · Computer Science 2025-10-23 Fali Wang , Hui Liu , Zhenwei Dai , Jingying Zeng , Zhiwei Zhang , Zongyu Wu , Chen Luo , Zhen Li , Xianfeng Tang , Qi He , Suhang Wang

We introduce Parametric Linear Dynamic Logic (PLDL), which extends Linear Dynamic Logic (LDL) by temporal operators equipped with parameters that bound their scope. LDL itself was proposed as an extension of Linear Temporal Logic (LTL) that…

Logic in Computer Science · Computer Science 2015-12-08 Peter Faymonville , Martin Zimmermann

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 present a new approach for benchmarking Large Language Model (LLM) capabilities on research-level mathematics. Existing benchmarks largely rely on static, hand-curated sets of contest or textbook-style problems as proxies for…

Artificial Intelligence · Computer Science 2026-03-02 Antoine Peyronnet , Fabian Gloeckle , Amaury Hayat

Centrality measures, quantifying the importance of vertices or edges, play a fundamental role in network analysis. To date, triggered by some positive approximability results, a large body of work has been devoted to studying centrality…

Social and Information Networks · Computer Science 2024-02-13 Atsushi Miyauchi , Lorenzo Severini , Francesco Bonchi

Outliers widely occur in big-data applications and may severely affect statistical estimation and inference. In this paper, a framework of outlier-resistant estimation is introduced to robustify an arbitrarily given loss function. It has a…

Methodology · Statistics 2023-04-20 Yiyuan She , Zhifeng Wang , Jiahui Shen

Ordinary Differential Equations are a simple but powerful framework for modeling complex systems. Parameter estimation from times series can be done by Nonlinear Least Squares (or other classical approaches), but this can give…

Methodology · Statistics 2014-10-29 Quentin Clairon , Nicolas Brunel

We present new integer linear programming (ILP) models for NP-hard optimisation problems in instances of the Stable Marriage problem with Ties and Incomplete lists (SMTI) and its many-to-one generalisation, the Hospitals / Residents problem…

Data Structures and Algorithms · Computer Science 2019-09-10 Maxence Delorme , Sergio García , Jacek Gondzio , Joerg Kalcsics , David Manlove , William Pettersson

Large language models (LLMs) have exhibited expert-level capabilities across various domains. However, their abilities to solve problems in Operations Research (OR) -- the analysis and optimization of mathematical models derived from…

Artificial Intelligence · Computer Science 2025-07-01 Akshit Kumar , Tianyi Peng , Yuhang Wu , Assaf Zeevi

There has been considerable recent interest in distribution-tests whose run-time and sample requirements are sublinear in the domain-size $k$. We study two of the most important tests under the conditional-sampling model where each query…

Data Structures and Algorithms · Computer Science 2015-04-17 Moein Falahatgar , Ashkan Jafarpour , Alon Orlitsky , Venkatadheeraj Pichapathi , Ananda Theertha Suresh

Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau…

Machine Learning · Computer Science 2026-04-22 Qingyang Zhang , Xinke Kong , Haitao Wu , Qinghua Hu , Minghao Wu , Baosong Yang , Yu Cheng , Yun Luo , Ganqu Cui , Changqing Zhang