English
Related papers

Related papers: Finite-size corrections in the random assignment p…

200 papers

We study optimization algorithms for the finite sum problems frequently arising in machine learning applications. First, we propose novel variants of stochastic gradient descent with a variance reduction property that enables linear…

Machine Learning · Computer Science 2017-07-06 Jakub Konečný

We propose a new algorithm for model-based distributional reinforcement learning (RL), and prove that it is minimax-optimal for approximating return distributions with a generative model (up to logarithmic factors), resolving an open…

Machine Learning · Computer Science 2024-11-05 Mark Rowland , Li Kevin Wenliang , Rémi Munos , Clare Lyle , Yunhao Tang , Will Dabney

We analyze a stochastic approximation algorithm for decision-dependent problems, wherein the data distribution used by the algorithm evolves along the iterate sequence. The primary examples of such problems appear in performative prediction…

Optimization and Control · Mathematics 2024-05-15 Joshua Cutler , Mateo Díaz , Dmitriy Drusvyatskiy

For a regression model, we consider the risk of the maximum likelihood estimator with respect to $\alpha$-divergence, which includes the special cases of Kullback-Leibler divergence, Hellinger distance and $\chi^2$ divergence. The…

Statistics Theory · Mathematics 2017-09-12 Yo Sheena

We consider the problem of estimating the factors of a rank-$1$ matrix with i.i.d. Gaussian, rank-$1$ measurements that are nonlinearly transformed and corrupted by noise. Considering two prototypical choices for the nonlinearity, we study…

Optimization and Control · Mathematics 2024-10-02 Kabir Aladin Chandrasekher , Mengqi Lou , Ashwin Pananjady

Saddle-point or primal-dual methods have recently attracted renewed interest as a systematic technique to design distributed algorithms which solve convex optimization problems. When implemented online for streaming data or as dynamic…

Optimization and Control · Mathematics 2021-04-22 John W. Simpson-Porco , Bala Kameshwar Poolla , Nima Monshizadeh , Florian Dorfler

We study numerically Anderson localization on lattices that are tree-like except for the presence of one loop of varying length $L$. The resulting expressions allow us to compute corrections to the Bethe lattice solution on i)…

Disordered Systems and Neural Networks · Physics 2023-10-17 Matilde Baroni , Giulia Garcia Lorenzana , Tommaso Rizzo , Marco Tarzia

In this paper, we tackle the resolution of chance-constrained problems reformulated via Sample Average Approximation. The resulting data-driven deterministic reformulation takes the form of a large-scale mixed-integer program cursed with…

Optimization and Control · Mathematics 2023-06-27 Álvaro Porras , Concepción Domínguez , Juan M. Morales , Salvador Pineda

We quantify a limitation in the usual accounting of the finite-size effects, where the leading $[(Z\alpha)^4]$ and subleading $[(Z\alpha)^5]$ contributions to the Lamb shift are given by the mean-square radius and the third Zemach moment of…

High Energy Physics - Phenomenology · Physics 2015-04-29 Franziska Hagelstein , Vladimir Pascalutsa

Large Language Models (LLMs) have demonstrated the capability to refine their generated answers through self-correction, enabling continuous performance improvement over multiple rounds. However, the mechanisms underlying how and why…

Computation and Language · Computer Science 2025-08-25 Zhe Yang , Yichang Zhang , Yudong Wang , Ziyao Xu , Junyang Lin , Zhifang Sui

Finite size effects for the Ising Model coupled to two dimensional random surfaces are studied by exploiting the exact results from the 2-matrix models. The fixed area partition function is numerically calculated with arbitrary precision by…

High Energy Physics - Theory · Physics 2009-10-28 N. D. Hari Dass , B. E. Hanlon , T. Yukawa

Many machine learning algorithms minimize a regularized risk, and stochastic optimization is widely used for this task. When working with massive data, it is desirable to perform stochastic optimization in parallel. Unfortunately, many…

Machine Learning · Statistics 2023-11-27 Shin Matsushima , Hyokun Yun , Xinhua Zhang , S. V. N. Vishwanathan

Response-adaptive randomization has recently attracted a lot of attention in the literature. In this paper, we propose a new and simple family of response-adaptive randomization procedures that attain the Cramer--Rao lower bounds on the…

Statistics Theory · Mathematics 2009-08-25 Feifang Hu , Li-Xin Zhang , Xuming He

This paper focuses on finding approximate solutions to stochastic optimal control problems with control domains being not necessarily convex, where the state trajectory is subject to controlled stochastic differential equations. The…

Optimization and Control · Mathematics 2025-07-15 Shaolin Ji , Rundong Xu

We discuss how various models of scale-free complex networks approach their limiting properties when the size N of the network grows. We focus mainly on equilibrated networks and their finite-size degree distributions. Our results show that…

Statistical Mechanics · Physics 2009-11-13 B. Waclaw , L. Bogacz , W. Janke

We analyse the forward error in the floating point summation of real numbers, from algorithms that do not require recourse to higher precision or better hardware. We derive informative explicit expressions, and new deterministic and…

Numerical Analysis · Mathematics 2021-07-06 Eric Hallman , Ilse C. F. Ipsen

In this paper we investigate the convergence of a recently popular class of first-order primal-dual algorithms for saddle point problems under the presence of errors occurring in the proximal maps and gradients. We study several types of…

Optimization and Control · Mathematics 2020-02-26 Julian Rasch , Antonin Chambolle

Critical phenomena on scale-free networks with a degree distribution $p_k \sim k^{-\lambda}$ exhibit rich finite-size effects due to its structural heterogeneity. We systematically study the finite-size scaling of percolation and identify…

Statistical Mechanics · Physics 2025-08-29 Xuewei Zhao , Liwenying Yang , Dan Peng , Run-Ran Liu , Ming Li

Two-timescale Stochastic Approximation (SA) algorithms are widely used in Reinforcement Learning (RL). Their iterates have two parts that are updated using distinct stepsizes. In this work, we develop a novel recipe for their finite sample…

Artificial Intelligence · Computer Science 2018-06-06 Gal Dalal , Balazs Szorenyi , Gugan Thoppe , Shie Mannor

Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific…

Machine Learning · Statistics 2016-04-12 Robert Nishihara , David Lopez-Paz , Léon Bottou