English
Related papers

Related papers: On the convergence of maximum variance unfolding

200 papers

This work unifies the analysis of various randomized methods for solving linear and nonlinear inverse problems by framing the problem in a stochastic optimization setting. By doing so, we show that many randomized methods are variants of a…

Numerical Analysis · Mathematics 2023-06-21 Jonathan Wittmer , C. G. Krishnanunni , Hai V. Nguyen , Tan Bui-Thanh

The high energy physics unfolding problem is an important statistical inverse problem in data analysis at the Large Hadron Collider (LHC) at CERN. The goal of unfolding is to make nonparametric inferences about a particle spectrum from…

Applications · Statistics 2017-06-09 Mikael Kuusela , Philip B. Stark

The Muon optimizer has demonstrated remarkable empirical success in handling matrix-structured parameters for training neural networks. However, a significant gap remains between its practical performance and theoretical understanding.…

Machine Learning · Computer Science 2026-05-12 Da Chang , Yongxiang Liu , Ganzhao Yuan

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

Consensus on nonlinear spaces is of use in many control applications. This paper proposes a gradient descent flow algorithm for consensus on hypersurfaces. We show that if an inequality holds, then the system converges for almost all…

Optimization and Control · Mathematics 2020-04-02 Johan Markdahl

Although overparameterized models have achieved remarkable practical success, their theoretical properties, particularly their generalization behavior, remain incompletely understood. The well known double descents phenomenon suggests that…

Machine Learning · Statistics 2026-01-06 Haoran Zhan , Yingcun Xia

In this paper, we produce explicit examples of mean curvature flow of (2m-1)-dimensional submanifolds which converge to (2m-2)-dimensional submanifolds at a finite time. These examples are a special class of hyperspheres in $\mathbb{C}^{m}$…

Differential Geometry · Mathematics 2023-09-11 Farnaz Ghanbari , Samreena

Optimization techniques are at the core of many scientific and engineering disciplines. The steepest descent methods play a foundational role in this area. In this paper we studied a generalized steepest descent method on Riemannian…

Optimization and Control · Mathematics 2025-02-28 Rashid A. , Amal A Samad

We derive multiscale statistics for deconvolution in order to detect qualitative features of the unknown density. An important example covered within this framework is to test for local monotonicity on all scales simultaneously. We…

Statistics Theory · Mathematics 2015-03-19 Johannes Schmidt-Hieber , Axel Munk , Lutz Duembgen

Multidimensional persistence studies topological features of shapes by analyzing the lower level sets of vector-valued functions. The rank invariant completely determines the multidimensional analogue of persistent homology groups. We prove…

Algebraic Topology · Mathematics 2009-08-04 Andrea Cerri , Barbara Di Fabio , Massimo Ferri , Patrizio Frosini , Claudia Landi

Three well-studied types of subgraph-restricted matchings are induced matchings, uniquely restricted matchings, and acyclic matchings. While it is hard to determine the maximum size of a matching of each of these types, whether some given…

Combinatorics · Mathematics 2017-10-24 M. Fürst , D. Rautenbach

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

In many experimental contexts, it is necessary to statistically remove the impact of instrumental effects in order to physically interpret measurements. This task has been extensively studied in particle physics, where the deconvolution…

High Energy Physics - Phenomenology · Physics 2024-12-17 Huanbiao Zhu , Krish Desai , Mikael Kuusela , Vinicius Mikuni , Benjamin Nachman , Larry Wasserman

We study the asymptotic behavior of a class of methods for sufficient dimension reduction in high-dimension regressions, as the sample size and number of predictors grow in various alignments. It is demonstrated that these methods are…

Statistics Theory · Mathematics 2012-05-31 R. Dennis Cook , Liliana Forzani , Adam J. Rothman

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study…

Optimization and Control · Mathematics 2018-10-30 Lenaic Chizat , Francis Bach

Supermodeling is a modern, model-ensembling paradigm that integrates several self-synchronized imperfect sub-models by controlling a few meta-parameters to generate more accurate predictions of complex systems' dynamics. Continual…

Computational Engineering, Finance, and Science · Computer Science 2021-03-01 Maciej Paszynski , Leszek Siwik , Witold Dzwinel , Keshav Pingali

Multivariate extreme-value analysis is concerned with the extremes in a multivariate random sample, that is, points of which at least some components have exceptionally large values. Mathematical theory suggests the use of max-stable models…

Probability · Mathematics 2012-04-03 Johan Segers

In this paper, the maximum spacing method is considered for multivariate observations. Nearest neighbour balls are used as a multidimensional analogue to univariate spacings. A class of information-type measures is used to generalize the…

Statistics Theory · Mathematics 2019-04-19 Kristi Kuljus , Bo Ranneby

It has previously been hypothesized, and supported with some experimental evidence, that deeper representations, when well trained, tend to do a better job at disentangling the underlying factors of variation. We study the following related…

Machine Learning · Computer Science 2012-07-19 Yoshua Bengio , Grégoire Mesnil , Yann Dauphin , Salah Rifai

The total variation distance is a core statistical distance between probability measures that satisfies the metric axioms, with value always falling in $[0,1]$. This distance plays a fundamental role in machine learning and signal…

Machine Learning · Computer Science 2018-07-02 Frank Nielsen , Ke Sun