English
Related papers

Related papers: Learning the Markov Decision Process in the Sparse…

200 papers

Markov decision problems (MDPs) provide the foundations for a number of problems of interest to AI researchers studying automated planning and reinforcement learning. In this paper, we summarize results regarding the complexity of solving…

Artificial Intelligence · Computer Science 2013-02-21 Michael L. Littman , Thomas L. Dean , Leslie Pack Kaelbling

We develop an exactly solvable framework of Markov decision process with a finite horizon, and continuous state and action spaces. We first review the exact solution of conventional linear quadratic regulation with a linear transition and a…

Machine Learning · Computer Science 2020-12-16 Yuan Yao , Xiaolin Sun

Inversion of sparse matrices with standard direct solve schemes is robust, but computationally expensive. Iterative solvers, on the other hand, demonstrate better scalability; but, need to be used with an appropriate preconditioner (e.g.,…

Numerical Analysis · Mathematics 2017-09-28 Hadi Pouransari , Pieter Coulier , Eric Darve

We consider the problem of computing optimal policies in average-reward Markov decision processes. This classical problem can be formulated as a linear program directly amenable to saddle-point optimization methods, albeit with a number of…

Optimization and Control · Mathematics 2020-01-13 Joan Bas-Serrano , Gergely Neu

A crucial task in system identification problems is the selection of the most appropriate model class, and is classically addressed resorting to cross-validation or using asymptotic arguments. As recently suggested in the literature, this…

Numerical Analysis · Mathematics 2015-06-09 Silvia Bonettini , Alessandro Chiuso , Marco Prato

Deep learning has been applied to various tasks in the field of machine learning and has shown superiority to other common procedures such as kernel methods. To provide a better theoretical understanding of the reasons for its success, we…

Machine Learning · Statistics 2023-05-31 Satoshi Hayakawa , Taiji Suzuki

Optimization of expensive computer models with the help of Gaussian process emulators in now commonplace. However, when several (competing) objectives are considered, choosing an appropriate sampling strategy remains an open question. We…

Optimization and Control · Mathematics 2013-10-03 Victor Picheny

In this work, we study several variants of matrix reduction via Gaussian elimination that try to keep the reduced matrix sparse. The motivation comes from the growing field of topological data analysis where matrix reduction is the major…

Computational Geometry · Computer Science 2024-06-14 Ulrich Bauer , Talha Bin Masood , Barbara Giunti , Guillaume Houry , Michael Kerber , Abhishek Rathod

This article proposes an efficient numerical method for solving nonlinear partial differential equations (PDEs) based on sparse Gaussian processes (SGPs). Gaussian processes (GPs) have been extensively studied for solving PDEs by…

Numerical Analysis · Mathematics 2023-08-09 Rui Meng , Xianjin Yang

Non-linear least squares solvers are used across a broad range of offline and real-time model fitting problems. Most improvements of the basic Gauss-Newton algorithm tackle convergence guarantees or leverage the sparsity of the underlying…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Huu Le , Christopher Zach , Edward Rosten , Oliver J. Woodford

The use of Gaussian process models is typically limited to datasets with a few tens of thousands of observations due to their complexity and memory footprint. The two most commonly used methods to overcome this limitation are 1) the…

Machine Learning · Statistics 2020-01-16 Vincent Adam , Stefanos Eleftheriadis , Nicolas Durrande , Artem Artemev , James Hensman

A q-Gauss-Newton algorithm is an iterative procedure that solves nonlinear unconstrained optimization problems based on minimization of the sum squared errors of the objective function residuals. Main advantage of the algorithm is that it…

Optimization and Control · Mathematics 2021-05-28 Danijela Protic , Miomir Stankovic

This paper explores a new framework for reinforcement learning based on online convex optimization, in particular mirror descent and related algorithms. Mirror descent can be viewed as an enhanced gradient method, particularly suited to…

Machine Learning · Computer Science 2012-10-19 Sridhar Mahadevan , Bo Liu

Inspired by biological vision systems, the over-complete local features with huge cardinality are increasingly used for face recognition during the last decades. Accordingly, feature selection has become more and more important and plays a…

Computer Vision and Pattern Recognition · Computer Science 2011-02-15 Yixiong Liang , Lei Wang , Yao Xiang , Beiji Zou

In this paper, we provide a novel algorithm for solving planning and learning problems of Markov decision processes. The proposed algorithm follows a policy iteration-type update by using a rank-one approximation of the transition…

Optimization and Control · Mathematics 2025-10-23 Arman Sharifi Kolarijani , Tolga Ok , Peyman Mohajerin Esfahani , Mohamad Amin Sharif Kolarijani

Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the $\ell_1$-norm. However, several important learning applications cannot benefit from this approach as…

Machine Learning · Computer Science 2013-04-11 Anastasios Kyrillidis , Stephen Becker , Volkan Cevher and , Christoph Koch

Sparse Bayesian Learning is one of the most popular sparse signal recovery methods, and various algorithms exist under the SBL paradigm. However, given a performance metric and a sparse recovery problem, it is difficult to know a-priori the…

Signal Processing · Electrical Eng. & Systems 2026-04-06 Rushabha Balaji , Kuan-Lin Chen , Danijela Cabric , Bhaskar D. Rao

We study the computational complexity of a very basic problem, namely that of finding solutions to a very large set of random linear equations in a finite Galois Field modulo q. Using tools from statistical mechanics we are able to identify…

Statistical Mechanics · Physics 2009-11-07 A. Braunstein , M. Leone , F. Ricci-Tersenghi , R. Zecchina

A linear inverse problem is proposed that requires the determination of multiple unknown signal vectors. Each unknown vector passes through a different system matrix and the results are added to yield a single observation vector. Given the…

Numerical Analysis · Computer Science 2010-09-03 Adam C. Zelinski , Vivek K Goyal , Elfar Adalsteinsson

One of the crucial tasks in many inference problems is the extraction of sparse information out of a given number of high-dimensional measurements. In machine learning, this is frequently achieved using, as a penality term, the $L_p$ norm…

Disordered Systems and Neural Networks · Physics 2012-02-09 Alejandro Lage-Castellanos , Andrea Pagnani , Martin Weigt