English
Related papers

Related papers: Universal Sequence Preconditioning

200 papers

Complex valued systems with an indefinite matrix term arise in important applications such as for certain time-harmonic partial differential equations such as the Maxwell's equation and for the Helmholtz equation. Complex systems with…

Numerical Analysis · Mathematics 2021-10-04 Owe Axelsson , Maeddeh Pourbagher , Davod Khojasteh Salkuyeh

We study the training dynamics of gradient descent in a softmax self-attention layer trained to perform linear regression and show that a simple first-order optimization algorithm can converge to the globally optimal self-attention…

Machine Learning · Computer Science 2026-03-03 Gautam Goel , Mahdi Soltanolkotabi , Peter Bartlett

The aim of this paper is to solve large-and-sparse linear Semidefinite Programs (SDPs) with low-rank solutions. We propose to use a preconditioned conjugate gradient method within second-order SDP algorithms and introduce a new efficient…

Optimization and Control · Mathematics 2021-05-19 Soodeh Habibi , Arefeh Kavand , Michal Kocvara , Michael Stingl

Adaptive regularization methods pre-multiply a descent direction by a preconditioning matrix. Due to the large number of parameters of machine learning problems, full-matrix preconditioning methods are prohibitively expensive. We show how…

Machine Learning · Computer Science 2020-11-19 Naman Agarwal , Brian Bullins , Xinyi Chen , Elad Hazan , Karan Singh , Cyril Zhang , Yi Zhang

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…

Machine Learning · Computer Science 2021-03-31 Giulia Denevi , Massimiliano Pontil , Carlo Ciliberto

This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information. Since LLMs are trained on massive text corpora using…

We aim to design strategies for sequential decision making that adjust to the difficulty of the learning problem. We study this question both in the setting of prediction with expert advice, and for more general combinatorial decision…

Machine Learning · Computer Science 2015-03-02 Wouter M. Koolen , Tim van Erven

The computational and storage complexity of kernel machines presents the primary barrier to their scaling to large, modern, datasets. A common way to tackle the scalability issue is to use the conjugate gradient algorithm, which relieves…

Machine Learning · Statistics 2016-05-26 Kurt Cutajar , Michael A. Osborne , John P. Cunningham , Maurizio Filippone

Online machine learning systems need to adapt to domain shifts. Meanwhile, acquiring label at every timestep is expensive. We propose a surprisingly simple algorithm that adaptively balances its regret and its number of label queries in…

Machine Learning · Computer Science 2021-03-01 Yining Chen , Haipeng Luo , Tengyu Ma , Chicheng Zhang

We define "decision swap regret" which generalizes both prediction for downstream swap regret and omniprediction, and give algorithms for obtaining it for arbitrary multi-dimensional Lipschitz loss functions in online adversarial settings.…

Machine Learning · Computer Science 2025-02-19 Jiuyao Lu , Aaron Roth , Mirah Shi

A candidate explanation of the good empirical performance of deep neural networks is the implicit regularization effect of first order optimization methods. Inspired by this, we prove a convergence theorem for nonconvex composite…

Machine Learning · Computer Science 2023-02-14 Dávid Terjék , Diego González-Sánchez

Long-term forecasting presents unique challenges due to the time and memory complexity of handling long sequences. Existing methods, which rely on sliding windows to process long sequences, struggle to effectively capture long-term…

Machine Learning · Computer Science 2024-03-26 Junwoo Park , Daehoon Gwak , Jaegul Choo , Edward Choi

We argue that the selective inclusion of data points based on latent objectives is common in practical situations, such as music sequences. Since this selection process often distorts statistical analysis, previous work primarily views it…

Machine Learning · Computer Science 2024-07-02 Yujia Zheng , Zeyu Tang , Yiwen Qiu , Bernhard Schölkopf , Kun Zhang

We propose a preconditioner that can accelerate the rate of convergence of the Multiple Shooting Shadowing (MSS) method. This recently proposed method can be used to compute derivatives of time-averaged objectives (also known as…

Numerical Analysis · Mathematics 2019-10-02 Karim Shawki , George Papadakis

We present an efficient and practical algorithm for the online prediction of discrete-time linear dynamical systems with a symmetric transition matrix. We circumvent the non-convex optimization problem using improper learning: carefully…

Machine Learning · Computer Science 2017-11-08 Elad Hazan , Karan Singh , Cyril Zhang

We present methods for online linear optimization that take advantage of benign (as opposed to worst-case) sequences. Specifically if the sequence encountered by the learner is described well by a known "predictable process", the algorithms…

Machine Learning · Statistics 2014-05-27 Alexander Rakhlin , Karthik Sridharan

Solomonoff completed the Bayesian framework by providing a rigorous, unique, formal, and universal choice for the model class and the prior. We discuss in breadth how and in which sense universal (non-i.i.d.) sequence prediction solves…

Machine Learning · Computer Science 2007-07-13 Marcus Hutter

We propose AllDiffPrecedence, a new global constraint that combines together an AllDifferent constraint with precedence constraints that strictly order given pairs of variables. We identify a number of applications for this global…

Artificial Intelligence · Computer Science 2011-03-22 Christian Bessiere , Nina Narodytska , Claude-Guy Quimper , Toby Walsh

We study learning to learn for the multi-task structured bandit problem where the goal is to learn a near-optimal algorithm that minimizes cumulative regret. The tasks share a common structure and an algorithm should exploit the shared…

Machine Learning · Computer Science 2025-10-24 Subhojyoti Mukherjee , Josiah P. Hanna , Qiaomin Xie , Robert Nowak

We develop an algorithmic theory of convex optimization over discrete sets. Using a combination of algebraic and geometric tools we are able to provide polynomial time algorithms for solving broad classes of convex combinatorial…

Optimization and Control · Mathematics 2009-01-24 Shmuel Onn
‹ Prev 1 4 5 6 7 8 10 Next ›