English
Related papers

Related papers: A Measure-Theoretic Analysis of Reasoning: Structu…

200 papers

Distribution shifts introduce uncertainty that undermines the robustness and generalization capabilities of machine learning models. While conventional wisdom suggests that learning causal-invariant representations enhances robustness to…

Machine Learning · Computer Science 2025-05-28 Abbavaram Gowtham Reddy , Celia Rubio-Madrigal , Rebekka Burkholz , Krikamol Muandet

The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…

Computation and Language · Computer Science 2025-03-31 Zhuo-Yang Song , Zeyu Li , Qing-Hong Cao , Ming-xing Luo , Hua Xing Zhu

We give a detailed survey of results obtained in the most recent half decade which led to a deeper understanding of the random displacement model, a model of a random Schr\"odinger operator which describes the quantum mechanics of an…

Mathematical Physics · Physics 2018-01-03 Frédéric Klopp , Michael Loss , Shu Nakamura , Günter Stolz

Reinforcement Learning with Verifiable Rewards (RLVR), primarily driven by the Group Relative Policy Optimization (GRPO) algorithm, is a leading approach for enhancing the reasoning abilities of Large Language Models (LLMs). Despite its…

Machine Learning · Computer Science 2025-10-21 Kangqi Ni , Zhen Tan , Zijie Liu , Pingzhi Li , Tianlong Chen

Large language models (LLMs) based on the Transformer have demonstrated strong performance across diverse tasks. However, current models still exhibit substantial limitations in out-of-distribution (OOD) generalization compared with humans.…

Machine Learning · Computer Science 2026-02-02 Huanyu Liu , Ge Li , Yihong Dong , Sihan Wu , Peixu Wang , Sihao Cheng , Taozhi Chen , Kechi Zhang , Hao Zhu , Tongxuan Liu

We show that on graphs with n vertices, the 2-dimensional Weisfeiler-Leman algorithm requires at most O(n^2/log(n)) iterations to reach stabilization. This in particular shows that the previously best, trivial upper bound of O(n^2) is…

Logic in Computer Science · Computer Science 2023-06-22 Sandra Kiefer , Pascal Schweitzer

Large language models (LLMs) must balance diversity and creativity against logical coherence in open-ended generation. Existing truncation-based samplers are effective but largely heuristic, relying mainly on probability mass and entropy…

Computation and Language · Computer Science 2026-05-15 Arash Gholami Davoodi , Navid Rezazadeh , Seyed Pouyan Mousavi Davoudi , Pouya Pezeshkpour

We study the large deviation rate functional for the empirical distribution of independent Brownian particles with drift. In one dimension, it has been shown by Adams, Dirr, Peletier and Zimmer that this functional is asymptotically…

Probability · Mathematics 2016-01-11 Matthias Erbar , Jan Maas , Michiel Renger

An easy consequence of Kantorovich-Rubinstein duality is the following: if $f:[0,1]^d \rightarrow \infty$ is Lipschitz and $\left\{x_1, \dots, x_N \right\} \subset [0,1]^d$, then $$ \left| \int_{[0,1]^d} f(x) dx - \frac{1}{N}…

Probability · Mathematics 2020-10-27 Stefan Steinerberger

Time series frequently manifest distribution shifts, diverse latent features, and non-stationary learning dynamics, particularly in open and evolving environments. These characteristics pose significant challenges for out-of-distribution…

Machine Learning · Computer Science 2026-05-20 Xin Wu , Fei Teng , Xingwang Li , Ji Zhang , Tianrui Li , Qiang Duan

Entropic regularization provides a simple way to approximate linear programs whose constraints split into two or more tractable blocks. The resulting objectives are amenable to cyclic Kullback-Leibler (KL) Bregman projections, with…

Optimization and Control · Mathematics 2026-05-11 Gabriel Peyré

Gradient Descent (GD) is a powerful workhorse of modern machine learning thanks to its scalability and efficiency in high-dimensional spaces. Its ability to find local minimisers is only guaranteed for losses with Lipschitz gradients, where…

Machine Learning · Computer Science 2023-07-27 Lei Chen , Joan Bruna

Traditional linear stability analysis based on matrix diagonalization is a computationally intensive $O(n^3)$ process for $n$-dimensional systems of differential equations, posing substantial limitations for the exploration of Turing…

Quantitative Methods · Quantitative Biology 2023-09-12 Roozbeh H. Pazuki , Robert G. Endres

Computation fundamentally separates time from space: nondeterministic search is exponential in time but polynomially simulable in space (Savitch's Theorem). We propose that the brain physically instantiates a biological variant of this…

Neurons and Cognition · Quantitative Biology 2025-12-02 Xin Li

In this paper, we present several new results on minimizing a nonsmooth and nonconvex function under a Lipschitz condition. Recent work shows that while the classical notion of Clarke stationarity is computationally intractable up to some…

Optimization and Control · Mathematics 2022-11-08 Michael I. Jordan , Tianyi Lin , Manolis Zampetakis

Wasserstein distributionally robust optimization offers a framework for model fitting in machine learning under potential shifts in the data distribution. We study a regularized variant of this problem in which entropic smoothing produces a…

Optimization and Control · Mathematics 2026-05-28 Tam Le

Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e.g., optimising the average-case risk, worst-case risk, or…

Machine Learning · Computer Science 2024-05-31 Anurag Singh , Siu Lun Chau , Shahine Bouabid , Krikamol Muandet

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

Optimal transport has emerged as a fundamental methodology with applications spanning multiple research areas in recent years. However, the convergence rate of the empirical estimator to its population counterpart suffers from the curse of…

Statistics Theory · Mathematics 2025-10-06 Jiaping Yang , Yunxin Zhang

Optimal transport (OT) and the related Wasserstein metric (W) are powerful and ubiquitous tools for comparing distributions. However, computing pairwise Wasserstein distances rapidly becomes intractable as cohort size grows. An attractive…

Machine Learning · Computer Science 2024-06-05 Doron Haviv , Russell Zhang Kunes , Thomas Dougherty , Cassandra Burdziak , Tal Nawy , Anna Gilbert , Dana Pe'er