English
Related papers

Related papers: Computational and Statistical Tradeoffs via Convex…

200 papers

We study some methods of subgradient projections for solving a convex feasibility problem with general (not necessarily hyperplanes or half-spaces) convex sets in the inconsistent case and propose a strategy that controls the relaxation…

Optimization and Control · Mathematics 2010-09-21 Dan Butnariu , Yair Censor , Pini Gurfil , Ethan Hadar

When dealing with datasets containing a billion instances or with simulations that require a supercomputer to execute, computational resources become part of the equation. We can improve the efficiency of learning and inference by…

Machine Learning · Computer Science 2014-03-06 Max Welling

The last decade witnessed a rise in the importance of supervised learning applications involving {\em big data} and {\em big models}. Big data refers to situations where the amounts of training data available and needed causes difficulties…

Optimization and Control · Mathematics 2018-11-01 Konstantin Mishchenko , Peter Richtárik

Low-rank modeling plays a pivotal role in signal processing and machine learning, with applications ranging from collaborative filtering, video surveillance, medical imaging, to dimensionality reduction and adaptive filtering. Many modern…

Machine Learning · Statistics 2018-05-04 Yudong Chen , Yuejie Chi

We investigate the effectiveness of convex relaxation and nonconvex optimization in solving bilinear systems of equations under two different designs (i.e.$~$a sort of random Fourier design and Gaussian design). Despite the wide…

Machine Learning · Statistics 2021-07-14 Yuxin Chen , Jianqing Fan , Bingyan Wang , Yuling Yan

We use the technique of information relaxation to develop a duality-driven iterative approach to obtaining and improving confidence interval estimates for the true value of finite-horizon stochastic dynamic programming problems. We show…

Optimization and Control · Mathematics 2020-07-29 Nan Chen , Xiang Ma , Yanchu Liu , Wei Yu

This paper firstly proposes a convex bilevel optimization paradigm to formulate and optimize popular learning and vision problems in real-world scenarios. Different from conventional approaches, which directly design their iteration schemes…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Risheng Liu , Long Ma , Xiaoming Yuan , Shangzhi Zeng , Jin Zhang

We propose a new randomized optimization method for high-dimensional problems which can be seen as a generalization of coordinate descent to random subspaces. We show that an adaptive sampling strategy for the random subspace significantly…

Optimization and Control · Mathematics 2019-12-19 Jonathan Lacotte , Mert Pilanci , Marco Pavone

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…

Methodology · Statistics 2013-06-25 Ping Ma , Michael W. Mahoney , Bin Yu

Sparse high dimensional graphical model selection is a topic of much interest in modern day statistics. A popular approach is to apply l1-penalties to either (1) parametric likelihoods, or, (2) regularized regression/pseudo-likelihoods,…

Methodology · Statistics 2022-02-04 Kshitij Khare , Sang-Yun Oh , Bala Rajaratnam

Canonical correlation analysis is a statistical technique that is used to find relations between two sets of variables. An important extension in pattern analysis is to consider more than two sets of variables. This problem can be expressed…

Machine Learning · Computer Science 2013-02-06 Jan Rupnik , Primoz Skraba , John Shawe-Taylor , Sabrina Guettes

We consider the problem of computing the maximal invariant set of discrete-time linear systems subject to a class of non-convex constraints that admit quadratic relaxations. These non-convex constraints include semialgebraic sets and other…

Systems and Control · Electrical Eng. & Systems 2020-11-30 Zheming Wang , Raphaël M. Jungers , Chong-Jin Ong

In this paper, we analyze in depth a simplicial decomposition like algorithmic framework for large scale convex quadratic programming. In particular, we first propose two tailored strategies for handling the master problem. Then, we…

Optimization and Control · Mathematics 2017-05-26 Enrico Bettiol , Lucas Létocart , Francesco Rinaldi , Emiliano Traversi

Modern applications require methods that are computationally feasible on large datasets but also preserve statistical efficiency. Frequently, these two concerns are seen as contradictory: approximation methods that enable computation are…

Methodology · Statistics 2021-06-11 Darren Homrighausen , Daniel J. McDonald

Exploring data requires a fast feedback loop from the analyst to the system, with a latency below about 10 seconds because of human cognitive limitations. When data becomes large or analysis becomes complex, sequential computations can no…

Human-Computer Interaction · Computer Science 2016-07-19 Jean-Daniel Fekete , Romain Primet

Statistical regression models whose mean functions are represented by ordinary differential equations (ODEs) can be used to describe phenomenons dynamical in nature, which are abundant in areas such as biology, climatology and genetics. The…

Methodology · Statistics 2017-05-15 Kyoungjae Lee , Jaeyong Lee , Sarat C. Dass

Gradient descent methods and especially their stochastic variants have become highly popular in the last decade due to their efficiency on big data optimization problems. In this thesis we present the development of data sampling strategies…

Optimization and Control · Mathematics 2018-04-03 Dominik Csiba

Why do neurons encode information the way they do? Normative answers to this question model neural activity as the solution to an optimisation problem; for example, the celebrated efficient coding hypothesis frames neural activity as the…

Neurons and Cognition · Quantitative Biology 2026-03-06 William Dorrell , Peter E. Latham , James Whittington

Sliced inverse regression is a popular tool for sufficient dimension reduction, which replaces covariates with a minimal set of their linear combinations without loss of information on the conditional distribution of the response given the…

Machine Learning · Statistics 2018-09-18 Kean Ming Tan , Zhaoran Wang , Tong Zhang , Han Liu , R. Dennis Cook

Spreading the information over all coefficients of a representation is a desirable property in many applications such as digital communication or machine learning. This so-called antisparse representation can be obtained by solving a convex…

Machine Learning · Computer Science 2020-07-15 Clément Elvira , Cédric Herzet