English
Related papers

Related papers: Tractability from overparametrization: The example…

200 papers

Considering the classification problem, we summarize the nonparallel support vector machines with the nonparallel hyperplanes to two types of frameworks. The first type constructs the hyperplanes separately. It solves a series of small…

Machine Learning · Computer Science 2021-06-28 Chun-Na Li , Yuan-Hai Shao , Huajun Wang , Yu-Ting Zhao , Ling-Wei Huang , Naihua Xiu , Nai-Yang Deng

Let $\Omega\subset\mathbb{R}^\nu$, $\nu\ge 2$, be a $C^{1,1}$ domain whose boundary $\partial\Omega$ is either compact or behaves suitably at infinity. For $p\in(1,\infty)$ and $\alpha>0$, define \[…

Spectral Theory · Mathematics 2017-04-27 Hynek Kovarik , Konstantin Pankrashkin

For probability measures on countable spaces we derive distributional limits for empirical entropic optimal transport quantities. More precisely, we show that the empirical optimal transport plan weakly converges to a centered Gaussian…

Probability · Mathematics 2022-12-27 Shayan Hundrieser , Marcel Klatt , Axel Munk

We improve the inequality used in Pronzato [2003. Removing non-optimal support points in D-optimum design algorithms. Statist. Probab. Lett. 63, 223-228] to remove points from the design space during the search for a $D$-optimum design. Let…

Statistics Theory · Mathematics 2007-07-02 Radoslav Harman , Luc Pronzato

We establish a precise connection between two elliptic quasilinear problems with Dirichlet data in a bounded domain of $\mathbb{R}^{N}.$ The first one, of the form \[ -\Delta_{p}u=\beta(u)| \nabla u| ^{p}+\lambda f(x)+\alpha, \] involves a…

Analysis of PDEs · Mathematics 2008-11-21 Haydar Abdel Hamid , Marie-Françoise Bidaut-Véron

In this paper, we study the predict-then-optimize problem where the output of a machine learning prediction task is used as the input of some downstream optimization problem, say, the objective coefficient vector of a linear program. The…

Machine Learning · Computer Science 2023-05-30 Chunlin Sun , Shang Liu , Xiaocheng Li

Statistical mechanics is used to study unrealizable generalization in two large feed-forward neural networks with binary weights and output, a perceptron and a tree committee machine. The student is trained by a teacher being larger, i.e.…

Condensed Matter · Physics 2007-05-23 Matts Sporre

We study information theoretic limits of recovering an unknown $n$ dimensional, complex signal vector $\mathbf{x}_\star$ with unit norm from $m$ magnitude-only measurements of the form $y_i = |(\mathbf{A} \mathbf{x}_\star)_i|^2, \; i = 1,2…

Statistics Theory · Mathematics 2020-08-05 Rishabh Dudeja , Junjie Ma , Arian Maleki

Statistical-physics calculations in machine learning and theoretical neuroscience often involve lengthy derivations that obscure physical interpretation. Here, we give concise, non-replica derivations of several key results and highlight…

Disordered Systems and Neural Networks · Physics 2025-10-29 David G. Clark , Haim Sompolinsky

We show that the maximal determinant D(n) for $n \times n$ ${\pm 1}$-matrices satisfies $R(n) := D(n)/n^{n/2} \ge \kappa_d > 0$. Here $n^{n/2}$ is the Hadamard upper bound, and $\kappa_d$ depends only on $d := n-h$, where $h$ is the maximal…

Combinatorics · Mathematics 2013-05-07 Richard P. Brent , Judy-anne H. Osborn , Warren D. Smith

In solving a system of $n$ linear equations in $d$ variables $Ax=b$, the condition number of the $n,d$ matrix $A$ measures how much errors in the data $b$ affect the solution $x$. Estimates of this type are important in many inverse…

Machine Learning · Computer Science 2020-04-29 Tomaso Poggio , Gil Kur , Andrzej Banburski

The estimation law of unknown parameters vector ${\theta}$ is proposed for one class of nonlinearly parametrized regression equations $y\left( t \right) = \Omega \left( t \right)\Theta \left( \theta \right)$. We restrict our attention to…

Systems and Control · Electrical Eng. & Systems 2023-08-22 Anton Glushchenko , Konstantin Lastochkin

Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of…

Understanding the character of electronic excitations is important in computational and reaction mechanistic studies, but their classification from simulations remains an open problem. Distances based on optimal transport have proven very…

Chemical Physics · Physics 2024-06-17 Annina Z. Lieberherr , Paola Gori-Giorgi , Klaas J. H. Giesbertz

The Support Vector Machine (SVM) is one of the most widely used classification methods. In this paper, we consider the soft-margin SVM used on data points with independent features, where the sample size $n$ and the feature dimension $p$…

Machine Learning · Statistics 2019-08-02 Haoyang Liu

Over-parametrization is an important technique in training neural networks. In both theory and practice, training a larger network allows the optimization algorithm to avoid bad local optimal solutions. In this paper we study a closely…

Machine Learning · Statistics 2020-10-23 Xiang Wang , Chenwei Wu , Jason D. Lee , Tengyu Ma , Rong Ge

Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. However, recent works show that one can…

Machine Learning · Statistics 2023-03-03 Florian Graf , Christoph D. Hofer , Marc Niethammer , Roland Kwitt

Data vectors generalise finite multisets: they are finitely supported functions into a commutative monoid. We study the question if a given data vector can be expressed as a finite sum of others, only assuming that 1) the domain is…

Logic in Computer Science · Computer Science 2016-10-06 Piotr Hofman , Jérôme Leroux , Patrick Totzke

In this note we give a new effective proof method for the equivalence of the notions of testability and nondeterministic testability for uniform hypergraph parameters. We provide the first effective upper bound on the sample complexity of…

Data Structures and Algorithms · Computer Science 2015-09-11 Marek Karpinski , Roland Markó

In high-dimensional classification settings, we wish to seek a balance between high power and ensuring control over a desired loss function. In many settings, the points most likely to be misclassified are those who lie near the decision…

Machine Learning · Statistics 2017-06-06 Arun Srinivasan
‹ Prev 1 3 4 5 6 7 10 Next ›