paper-with-me

홈 › Papers

A Statistical Perspective on Algorithmic Leveraging

2013-06-23 · Ping Ma, Michael W. Mahoney, Bin Yu

One popular method for dealing with large-scale data sets is sampling. For example, by using the empirical statistical leverage scores as an importance sampling distribution, the method of algorithmic leveraging samples and rescales rows/columns of data matrices to reduce the data size before performing computations on the subproblem. This method has been successful in improving computational efficiency of algorithms for matrix problems such as least-squares approximation, least absolute deviations approximation, and low-rank matrix approximation. Existing work has focused on algorithmic issues such as worst-case running times and numerical issues associated with providing high-quality implementations, but none of it addresses statistical aspects of this method. In this paper, we provide a simple yet effective framework to evaluate the statistical properties of algorithmic leveraging in the context of estimating parameters in a linear regression model with a fixed number of predictors. We show that from the statistical perspective of bias and variance, neither leverage-based sampling nor uniform sampling dominates the other. This result is particularly striking, given the well-known result that, from the algorithmic perspective of worst-case analysis, leverage-based sampling provides uniformly superior worst-case algorithmic results, when compared with uniform sampling. Based on these theoretical results, we propose and analyze two new leveraging algorithms. A detailed empirical evaluation of existing leverage-based methods as well as these two new methods is carried out on both synthetic and real data sets. The empirical results indicate that our theory is a good predictor of practical performance of existing and new leverage-based algorithms and that the new algorithms achieve improved performance.

📄 PDF Abstract BibTeX arXiv:1306.5362

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Statistical and Algorithmic Perspectives on Randomized Sketching for Ordinary Least-Squares -- ICML

2015-05-25 · Garvesh Raskutti, Michael Mahoney

We consider statistical and algorithmic aspects of solving large-scale least-squares (LS) problems using randomized sketching algorithms. Prior results show that, from an \emph{algorithmic perspective}, when using sketch…

A Statistical Perspective on Randomized Sketching for Ordinary Least-Squares

2014-06-23 · Garvesh Raskutti, Michael Mahoney

We consider statistical as well as algorithmic aspects of solving large-scale least-squares (LS) problems using randomized sketching algorithms. For a LS problem with input data $(X, Y) \in \mathbb{R}^{n \times p} \times…

Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity

2024-10-23 · Philip Amortila, Dylan J. Foster, Nan Jiang, Akshay Krishnamurthy 외

Real-world applications of reinforcement learning often involve environments where agents operate on complex, high-dimensional observations, but the underlying (''latent'') dynamics are comparatively simple. However, out…

reinforcement-learningReinforcement Learning

A Theoretical Analysis of Deep Q-Learning

2019-01-01 · Jianqing Fan, Zhaoran Wang, Yuchen Xie, Zhuoran Yang

Despite the great empirical success of deep reinforcement learning, its theoretical foundation is less well understood. In this work, we make the first attempt to theoretically understand the deep Q-network (DQN) algorit…

Deep Reinforcement LearningQ-LearningReinforcement Learning

Implicit Statistical Inference in Transformers: Approximating Likelihood-Ratio Tests In-Context

2026-03-11 · Faris Chaudhry, Siddhant Gadkari arxiv

In-context learning (ICL) allows Transformers to adapt to novel tasks without weight updates, yet the underlying algorithms remain poorly understood. We adopt a statistical decision-theoretic perspective by investigating…