English
Related papers

Related papers: Multiplication-Avoiding Variant of Power Iteration…

200 papers

Principal component analysis (PCA) is known to be sensitive to outliers, so that various robust PCA variants were proposed in the literature. A recent model, called REAPER, aims to find the principal components by solving a convex…

Numerical Analysis · Mathematics 2021-03-19 Robert Beinert , Gabriele Steidl

In this paper, we propose a cone projected power iteration algorithm to recover the first principal eigenvector from a noisy positive semidefinite matrix. When the true principal eigenvector is assumed to belong to a convex cone, the…

Statistics Theory · Mathematics 2021-03-02 Yufei Yi , Matey Neykov

Tensor decomposition serves as a powerful primitive in statistics and machine learning, and has numerous applications in problems such as learning latent variable models or mixture of Gaussians. In this paper, we focus on using power…

Machine Learning · Computer Science 2025-03-25 Yuchen Wu , Kangjie Zhou

We study reinforcement learning in infinite-horizon average-reward settings with linear MDPs. Previous work addresses this problem by approximating the average-reward setting by discounted setting and employing a value iteration-based…

Machine Learning · Computer Science 2025-04-17 Kihyuk Hong , Ambuj Tewari

To overcome the performance limitations in modern computing, such as the power wall, emerging computing paradigms are gaining increasing importance. Approximate computing offers a promising solution by substantially enhancing energy…

Emerging Technologies · Computer Science 2024-12-23 Melanie Qiu , Caoyueshan Fan , Gulafshan , Salar Shakibhamedan , Fabian Seiler , Nima TaheriNejad

Representation intervention has emerged as a promising paradigm for aligning large language models toward desired behaviors without modifying model weights. Existing methods typically apply a fixed intervention uniformly across all inputs.…

Artificial Intelligence · Computer Science 2026-05-28 Manjiang Yu , Hongji Li , Junwei Chen , Xue Li , Priyanka Singh , Yang Cao , Lijie Hu

Value iteration (VI) is a ubiquitous algorithm for optimal control, planning, and reinforcement learning schemes. Under the right assumptions, VI is a vital tool to generate inputs with desirable properties for the controlled system, like…

Optimization and Control · Mathematics 2020-11-23 Mathieu Granzotto , Romain Postoyan , Dragan Nešić , Lucian Buşoniu , Jamal Daafouz

The objective of this research was to compute the principal matrix square root with sparse approximation. A new stable iterative scheme avoiding fully matrix inversion (SIAI) is provided. The analysis on the sparsity and error of the…

Numerical Analysis · Mathematics 2022-06-22 Li Zhu , Keqi Ye , Yuelin Zhao , Feng Wu , Jiqiang Hu , Wanxie Zhong

Policy iteration (PI) is a recursive process of policy evaluation and improvement for solving an optimal decision-making/control problem, or in other words, a reinforcement learning (RL) problem. PI has also served as the fundamental for…

Artificial Intelligence · Computer Science 2021-04-06 Jaeyoung Lee , Richard S. Sutton

Power ISA(TM) Version 3.1 has introduced a new family of matrix math instructions, collectively known as the Matrix-Multiply Assist (MMA) facility. The instructions in this facility implement numerical linear algebra operations on small…

Matrix factorization is a simple and effective solution to the recommendation problem. It has been extensively employed in the industry and has attracted much attention from the academia. However, it is unclear what the low-dimensional…

Machine Learning · Computer Science 2018-08-29 Farhan Khawar , Nevin L. Zhang

Mixed-numerology transmission is proposed to support a variety of communication scenarios with diverse requirements. However, as the orthogonal frequency division multiplexing (OFDM) remains as the basic waveform, the peak-to average power…

Signal Processing · Electrical Eng. & Systems 2019-11-06 Xiaoran Liu , Xiaoying Zhang , Lei Zhang , Pei Xiao , Jibo Wei , Haijun Zhang , Victor C. M. Leung

Matrix multiplication is a fundamental operation in both training of neural networks and inference. To accelerate matrix multiplication, Graphical Processing Units (GPUs) provide it implemented in hardware. Due to the increased throughput…

Mathematical Software · Computer Science 2026-04-07 Faizan A. Khattak , Mantas Mikaitis

In the note we consider an iterative generalisation of the rejection sampling method. In high energy physics, this sampling is frequently used for event generation, i.e. preparation of phase space points distributed according to a matrix…

High Energy Physics - Phenomenology · Physics 2008-07-18 A. Sherstnev

We present an algorithm to reduce the computational effort for the multiplication of a given matrix with an unknown column vector. The algorithm decomposes the given matrix into a product of matrices whose entries are either zero or integer…

Information Theory · Computer Science 2020-02-28 Ralf R. Müller , Bernhard Gäde , Ali Bereyhi

Magnetic resonance imaging (MRI) is a non-invasive medical imaging technique offering high-resolution 3D images and valuable insights into human tissue conditions. Even at present, the refinement of denoising methods for MRI remains a…

Image and Video Processing · Electrical Eng. & Systems 2023-08-29 Shiao Li

Given a Markov Decision Process (MDP) with $n$ states and a totalnumber $m$ of actions, we study the number of iterations needed byPolicy Iteration (PI) algorithms to converge to the optimal$\gamma$-discounted policy. We consider two…

Optimization and Control · Mathematics 2016-02-11 Bruno Scherrer

We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual value-function learning step with a learning step in policy…

Artificial Intelligence · Computer Science 2011-09-13 A. Fern , R. Givan , S. Yoon

Howard's Policy Iteration (HPI) is a classic algorithm for solving Markov Decision Problems (MDPs). HPI uses a "greedy" switching rule to update from any non-optimal policy to a dominating one, iterating until an optimal policy is found.…

Artificial Intelligence · Computer Science 2025-05-05 Dibyangshu Mukherjee , Shivaram Kalyanakrishnan

Recent control algorithms for Markov decision processes (MDPs) have been designed using an implicit analogy with well-established optimization algorithms. In this paper, we adopt the quasi-Newton method (QNM) from convex optimization to…

Optimization and Control · Mathematics 2026-01-06 Mohammad Amin Sharifi Kolarijani , Peyman Mohajerin Esfahani