English
Related papers

Related papers: Zero-One Laws for Random Feasibility Problems

200 papers

We investigate moment sequences of probability measures on $E\subset\mathbb{R}$ under constraints of certain moments being fixed. This corresponds to studying sections of $n$-th moment spaces, i.e. the spaces of moment sequences of order…

Probability · Mathematics 2022-12-12 Holger Dette , Dominik Tomecki , Martin Venker

Sparse learning has recently received increasing attention in many areas including machine learning, statistics, and applied mathematics. The mixed-norm regularization based on the L1/Lq norm with q > 1 is attractive in many applications of…

Machine Learning · Computer Science 2010-09-27 Jun Liu , Jieping Ye

We first describe a general class of optimization problems that describe many natural, economic, and statistical phenomena. After noting the existence of a conserved quantity in a transformed coordinate system, we outline several instances…

Optimization and Control · Mathematics 2018-04-03 David Rushing Dewhurst

Finding a point in the intersection of a collection of closed convex sets, that is the convex feasibility problem, represents the main modeling strategy for many computational problems. In this paper we analyze new stochastic reformulations…

Optimization and Control · Mathematics 2018-01-16 Ion Necoara , Peter Richtarik , Andrei Patrascu

We study the problem of learning general (i.e., not necessarily homogeneous) halfspaces with Random Classification Noise under the Gaussian distribution. We establish nearly-matching algorithmic and Statistical Query (SQ) lower bound…

Machine Learning · Computer Science 2023-07-18 Ilias Diakonikolas , Jelena Diakonikolas , Daniel M. Kane , Puqian Wang , Nikos Zarifis

Recent studies of under-determined linear systems of equations with sparse solutions showed a great practical and theoretical efficiency of a particular technique called $\ell_1$-optimization. Seminal works \cite{CRT,DOnoho06CS} rigorously…

Information Theory · Computer Science 2013-06-18 Mihailo Stojnic

We study a tight Bennett-type concentration inequality for sums of heterogeneous and independent variables, defined as a one-dimensional minimization. We show that this refinement, which outperforms the standard known bounds, remains…

Optimization and Control · Mathematics 2022-11-23 Quentin Jacquet , Riadh Zorgati

One of the main problems in random network coding is to compute good lower and upper bounds on the achievable cardinality of the so-called subspace codes in the projective space $\mathcal{P}_q(n)$ for a given minimum distance. The…

Information Theory · Computer Science 2020-11-16 Tao Feng , Sascha Kurz , Shuangqing Liu

We study the expressibility and learnability of convex optimization solution functions and their multi-layer architectural extension. The main results are: \emph{(1)} the class of solution functions of linear programming (LP) and quadratic…

Machine Learning · Computer Science 2022-12-05 Ming Jin , Vanshaj Khattar , Harshal Kaushik , Bilgehan Sel , Ruoxi Jia

The likelihood function of a finite mixture model is a non-convex function with multiple local maxima and commonly used iterative algorithms such as EM will converge to different solutions depending on initial conditions. In this paper we…

Machine Learning · Computer Science 2016-08-19 Elad Mezuman , Yair Weiss

Submodular optimization generalizes many classic problems in combinatorial optimization and has recently found a wide range of applications in machine learning (e.g., feature engineering and active learning). For many large-scale…

Data Structures and Algorithms · Computer Science 2023-04-11 Matthew Fahrbach , Vahab Mirrokni , Morteza Zadimoghaddam

We study the problem of modeling univariate distributions via their quantile functions. We introduce a flexible family of distributions whose quantile function is a linear combination of basis quantiles. Because the model is linear in its…

Methodology · Statistics 2026-02-05 Cheng Peng , Yizhou Li , Stan Uryasev

We study the problem of learning mixtures of linear classifiers under Gaussian covariates. Given sample access to a mixture of $r$ distributions on $\mathbb{R}^n$ of the form $(\mathbf{x},y_{\ell})$, $\ell\in [r]$, where…

Machine Learning · Computer Science 2023-10-19 Ilias Diakonikolas , Daniel M. Kane , Yuxin Sun

Machine learning approaches relying on such criteria as adversarial robustness or multi-agent settings have raised the need for solving game-theoretic equilibrium problems. Of particular relevance to these applications are methods targeting…

Machine Learning · Computer Science 2023-10-27 Xufeng Cai , Ahmet Alacaoglu , Jelena Diakonikolas

The development, assessment, and comparison of randomized search algorithms heavily rely on benchmarking. Regarding the domain of constrained optimization, the number of currently available benchmark environments bears no relation to the…

Neural and Evolutionary Computing · Computer Science 2018-07-27 Michael Hellwig , Hans-Georg Beyer

We deal with the problem, initiated in [8], of finding randomized and quantum complexity of initial-value problems. We showed in [8] that a speed-up in both settings over the worst-case deterministic complexity is possible. In the present…

Quantum Physics · Physics 2007-05-23 Boleslaw Kacewicz

In the absence of prior knowledge, ordinal embedding methods obtain new representation for items in a low-dimensional Euclidean space via a set of quadruple-wise comparisons. These ordinal comparisons often come from human annotators, and…

Machine Learning · Computer Science 2018-12-06 Ke Ma , Qianqian Xu , Zhiyong Yang , Xiaochun Cao

Two widely-used computational paradigms for sublinear algorithms are using linear measurements to perform computations on a high dimensional input and using structured queries to access a massive input. Typically, algorithms in the former…

Computational Complexity · Computer Science 2021-07-14 Amit Chakrabarti , Manuel Stoeckl

The l1-regularization is very popular in high dimensional statistics -- it changes a combinatorial problem of choosing which subset of the parameter are zero, into a simple continuous optimization. Using a continuous prior concentrated near…

Methodology · Statistics 2023-02-22 Maoran Xu , Leo L. Duan

Generalised linear models for multi-class classification problems are one of the fundamental building blocks of modern machine learning tasks. In this manuscript, we characterise the learning of a mixture of $K$ Gaussians with generic means…