English
Related papers

Related papers: Preconditioning to comply with the Irrepresentable…

200 papers

Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting…

Artificial Intelligence · Computer Science 2025-10-14 Martina G. Vilas , Safoora Yousefi , Besmira Nushi , Eric Horvitz , Vidhisha Balachandran

Conditional forecasts, i.e. projections of a set of variables of interest on the future paths of some other variables, are used routinely by empirical macroeconomists in a number of applied settings. In spite of this, the existing…

Econometrics · Economics 2024-07-03 Joshua C. C. Chan , Davide Pettenuzzo , Aubrey Poon , Dan Zhu

Learning sparse models from data is an important task in all those frameworks where relevant information should be identified within a large dataset. This can be achieved by formulating and solving suitable sparsity promoting optimization…

Optimization and Control · Mathematics 2025-02-18 V. Cerone , S. M. Fosson , D. Regruto , A. Salam

We present a modified version of the PRESB preconditioner for two-by-two block system of linear equations with the coefficient matrix $$\textbf{A}=\left(\begin{array}{cc} F & -G^* G & F \end{array}\right),$$ where $F\in\mathbb{C}^{n\times…

Numerical Analysis · Mathematics 2024-05-15 Owe Axelsson , Dovod Khojasteh Slakuyeh

The attention mechanism is the key to large language models, and the attention matrix serves as an algorithmic and computational bottleneck for such a scheme. In this paper, we define two problems, motivated by designing fast algorithms for…

Machine Learning · Computer Science 2024-04-03 Zhao Song , Junze Yin , Lichen Zhang

We study the problem of preconditioning in sequential prediction. From the theoretical lens of linear dynamical systems, we show that convolving the target sequence corresponds to applying a polynomial to the hidden transition matrix.…

Machine Learning · Computer Science 2026-01-29 Annie Marsden , Elad Hazan

When data contains measurement errors, it is necessary to make assumptions relating the observed, erroneous data to the unobserved true phenomena of interest. These assumptions should be justifiable on substantive grounds, but are often…

Machine Learning · Statistics 2020-12-24 Noam Finkelstein , Roy Adams , Suchi Saria , Ilya Shpitser

We study first-order methods with preconditioning for solving structured nonlinear convex optimization problems. We propose a new family of preconditioners generated by symmetric polynomials. They provide first-order optimization methods…

Optimization and Control · Mathematics 2023-01-31 Nikita Doikov , Anton Rodomanov

Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently,…

Machine Learning · Computer Science 2020-01-10 Zhiqing Sun , Zhuohan Li , Haoqing Wang , Zi Lin , Di He , Zhi-Hong Deng

We describe an algorithm that, given any full-rank matrix A having fewer rows than columns, can rapidly compute the orthogonal projection of any vector onto the null space of A, as well as the orthogonal projection onto the row space of A,…

Numerical Analysis · Computer Science 2011-05-26 Vladimir Rokhlin , Mark Tygert

Parsimony, including sparsity and low rank, has been shown to successfully model data in numerous machine learning and signal processing tasks. Traditionally, such modeling approaches rely on an iterative algorithm that minimizes an…

Machine Learning · Computer Science 2012-12-18 Pablo Sprechmann , Alex M. Bronstein , Guillermo Sapiro

The conjugate gradient solver (CG) is a prevalent method for solving symmetric and positive definite linear systems Ax=b, where effective preconditioners are crucial for fast convergence. Traditional preconditioners rely on prescribed…

Machine Learning · Computer Science 2025-11-03 Zherui Yang , Zhehao Li , Kangbo Lyu , Yixuan Li , Tao Du , Ligang Liu

The LASSO is a recent technique for variable selection in the regression model \bean y & = & X\beta + z, \eean where $X\in \R^{n\times p}$ and $z$ is a centered gaussian i.i.d. noise vector $\mathcal N(0,\sigma^2I)$. The LASSO has been…

Statistics Theory · Mathematics 2023-12-21 Mohamed Ibrahim Assoweh , Emmanuel Caron , Stéphane Chrétien

We consider the problem of finding the optimal diagonal preconditioner for a positive definite matrix. Although this problem has been shown to be solvable and various methods have been proposed, none of the existing approaches are scalable…

Numerical Analysis · Mathematics 2024-11-07 Wenzhi Gao , Zhaonan Qu , Madeleine Udell , Yinyu Ye

In this article we investigate consistency of selection in regression models via the popular Lasso method. Here we depart from the traditional linear regression assumption and consider approximations of the regression function $f$ with…

Statistics Theory · Mathematics 2008-12-18 Florentina Bunea

State-of-the-art saliency prediction methods develop upon model architectures or loss functions; while training to generate one target saliency map. However, publicly available saliency prediction datasets can be utilized to create more…

Computer Vision and Pattern Recognition · Computer Science 2020-09-01 Sandeep Mishra , Oindrila Saha

Accurate and explainable artificial-intelligence (AI) models are promising tools for the acceleration of the discovery of new materials, ore new applications for existing materials. Recently, symbolic regression has become an increasingly…

Data Analysis, Statistics and Probability · Physics 2023-05-03 Thomas A. R. Purcell , Matthias Scheffler , Luca M. Ghiringhelli

The ultimate goal of regression analysis is to obtain information about the conditional distribution of a response given a set of explanatory variables. This goal is, however, seldom achieved because most established regression models only…

Methodology · Statistics 2017-12-13 Torsten Hothorn , Thomas Kneib , Peter Bühlmann

The main computational cost of algorithms for computing reduced-order models of parametric dynamical systems is in solving sequences of very large and sparse linear systems. We focus on efficiently solving these linear systems, arising…

Numerical Analysis · Mathematics 2018-09-19 Navneet Pratap Singh , Kapil Ahuja

Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data to learn useful semantic representations. These pretext tasks are created solely using the input features,…

Machine Learning · Computer Science 2021-11-16 Jason D. Lee , Qi Lei , Nikunj Saunshi , Jiacheng Zhuo