analiza aiqbench
This paper introduces Asymptotics Learning Theory (ALT), a novel framework that unifies optimization with asymptotic analysis to rigorously compute unknown parameters in mathematical expansions. By developing sliding Linear Least Squares methods with proven convergence-rate guarantees, the authors address critical limitations like slow convergence or divergence found in existing techniques for analytic combinatorics and discrete structures. While highly relevant to theoretical machine learning foundations, this work focuses on pure mathematical optimization rather than applied AI models or quantum systems.
Learning Asymptotics with Convergence-Rate Guarantees using Linear Least Squares
arXiv:2607.23287v1 Announce Type: cross Abstract: We introduce a new research area that is called Asymptotics Learning Theory (ALT) and combines optimization with asymptotic analysis. In particular, ALT provides a unified approach for computing unknown constants/parameters in proven asymptotic expansions using optimization theory. In this paper, we focus on a general asymptotic form which includes a broad class of asymptotics. Furthermore, we study two powerful numerical methods, namely, sliding Linear Least Squares (sLLSQ) and sliding Tikhonov Linear Least Squares (sT-LLSQ). For these techniques we rigorously prove asymptotic estimates that lead to sufficient conditions for convergence (to the correct values of unknown parameters) and convergence-rate guarantees. Despite their strengths, both methods have also limitations, e.g., slow convergence---or even, counterintuitively, divergence---in some cases. Moreover, we present fundamental applications in analytic combinatorics, a beautiful field of mathematics that deals with asymptotic enumeration of discrete structures using complex analysis. The proposed techniques complement existing approaches, such as the ratio method and its variants. Numerical examples also verify the theoretical results. Finally, we discuss interesting research directions in ALT.
Abstract:We introduce a new research area that is called Asymptotics Learning Theory (ALT) and combines optimization with asymptotic analysis. In particular, ALT provides a unified approach for computing unknown constants/parameters in proven asymptotic expansions using optimization theory. In this paper, we focus on a general asymptotic form which includes a broad class of asymptotics. Furthermore, we study two powerful numerical methods, namely, sliding Linear Least Squares (sLLSQ) and sliding Tikhonov Linear Least Squares (sT-LLSQ). For these techniques we rigorously prove asymptotic estimates that lead to sufficient conditions for convergence (to the correct values of unknown parameters) and convergence-rate guarantees. Despite their strengths, both methods have also limitations, e.g., slow convergence---or even, counterintuitively, divergence---in some cases. Moreover, we present fundamental applications in analytic combinatorics, a beautiful field of mathematics that deals with asymptotic enumeration of discrete structures using complex analysis. The proposed techniques complement existing approaches, such as the ratio method and its variants. Numerical examples also verify the theoretical results. Finally, we discuss interesting research directions in ALT.
Machine Learning (stat.ML); Machine Learning (cs.LG); Combinatorics (math.CO); Numerical Analysis (math.NA)
arXiv:2607.23287 [stat.ML]
(or arXiv:2607.23287v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2607.23287 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 270 cuvinte
Subiecte conexe
Exploding variance of means of exponentials: least-squares to the rescue – Machine Learning Research Blog
francisbach.com · 27 sept. 2026
Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits
arXiv · 2 oct. 2026
DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks
arXiv · 25 aug. 2026
Deconfusing Corrigibility
AI Alignment Forum · 17 oct. 2026