English
Related papers

Related papers: Global Minimum Depth In Edwards-Anderson Model

200 papers

We consider a two-dimensional MHD model describing the evolution of viscous, compressible and electrically conducting fluids under the action of vertical magnetic field without resistivity. Existence of global weak solutions is established…

Analysis of PDEs · Mathematics 2019-07-02 Yang Li , Yongzhong Sun

Metric embeddings are a widely used method in algorithm design, where generally a ``complex'' metric is embedded into a simpler, lower-dimensional one. Historically, the theoretical computer science community has focused on bi-Lipschitz…

Data Structures and Algorithms · Computer Science 2025-05-19 Ainesh Bakshi , Vincent Cohen-Addad , Samuel B. Hopkins , Rajesh Jayaram , Silvio Lattanzi

In this paper, we prove that an Adam-type algorithm with smooth clipping approaches the global minimizer of the regularized non-convex loss function. Adding smooth clipping and taking the state space as the set of all trajectories, we can…

Machine Learning · Computer Science 2023-12-06 Keisuke Suzuki

For any finite point set in $D$-dimensional space equipped with the 1-norm, we present random linear embeddings to $k$-dimensional space, with a new metric, having the following properties. For any pair of points from the point set that are…

Probability · Mathematics 2020-11-09 Michael P. Casey

We study the minimum diameter problem for a set of inexact points. By inexact, we mean that the precise location of the points is not known. Instead, the location of each point is restricted to a contineus region ($\impre$ model) or a…

Computational Geometry · Computer Science 2017-04-03 Mohammad Ghodsi , Hamid Homapour , Masoud Seddighin

The two-dimensional (2D) incompressible Euler equations have been thoroughly investigated and the resolution of the global (in time) existence and uniqueness issue is currently in a satisfactory status. In contrast, the global regularity…

Analysis of PDEs · Mathematics 2013-08-09 Dhanapati Adhikari , Chongsheng Cao , Jiahong Wu , Xiaojing Xu

Recently, there has been a growing focus on determining the minimum width requirements for achieving the universal approximation property in deep, narrow Multi-Layer Perceptrons (MLPs). Among these challenges, one particularly challenging…

Machine Learning · Computer Science 2023-11-08 Geonho Hwang

High-dimensional data are ubiquitous in contemporary science and finding methods to compress them is one of the primary goals of machine learning. Given a dataset lying in a high-dimensional space (in principle hundreds to several thousands…

Machine Learning · Computer Science 2020-03-24 Vittorio Erba , Marco Gherardi , Pietro Rotondo

We provide exact asymptotic expressions for the performance of regression by an $L-$layer deep random feature (RF) model, where the input is mapped through multiple random embedding and non-linear activation functions. For this purpose, we…

Machine Learning · Statistics 2023-02-14 David Bosch , Ashkan Panahi , Babak Hassibi

For nonconvex optimization in machine learning, this article proves that every local minimum achieves the globally optimal value of the perturbable gradient basis model at any differentiable point. As a result, nonconvex machine learning is…

Machine Learning · Statistics 2019-11-19 Kenji Kawaguchi , Jiaoyang Huang , Leslie Pack Kaelbling

Low-dimensional embeddings are essential for machine learning tasks involving graphs, such as node classification, link prediction, community detection, network visualization, and network compression. Although recent studies have identified…

Machine Learning · Computer Science 2025-03-04 Nikolaos Nakis , Niels Raunkjær Holm , Andreas Lyhne Fiehn , Morten Mørup

We prove that the finite-difference based derivative-free descent (FD-DFD) methods have a capability to find the global minima for a class of multiple minima problems. Our main result shows that, for a class of multiple minima objectives…

Optimization and Control · Mathematics 2020-06-26 Xiaopeng Luo , Xin Xu , Daoyi Dong

The conventional Minimum Error Entropy criterion (MEE) has its limitations, showing reduced sensitivity to error mean values and uncertainty regarding error probability density function locations. To overcome this, a MEE with fiducial…

Signal Processing · Electrical Eng. & Systems 2023-09-12 Haiquan Zhao , Yuan Gao , Yingying Zhu

We describe a non-parametric, "example-based" method for estimating the depth of an object, viewed in a single photo. Our method consults a database of example 3D geometries, searching for those which look similar to the object in the…

Computer Vision and Pattern Recognition · Computer Science 2013-04-16 Tal Hassner , Ronen Basri

Recent advances in deep learning optimization have unveiled two intriguing phenomena under large learning rates: Edge of Stability (EoS) and Progressive Sharpening (PS), challenging classical Gradient Descent (GD) analyses. Current research…

Machine Learning · Computer Science 2025-03-05 Liming Liu , Zixuan Zhang , Simon Du , Tuo Zhao

The traditional sparse modeling approach, when applied to inverse problems with large data such as images, essentially assumes a sparse model for small overlapping data patches. While producing state-of-the-art results, this methodology is…

Information Theory · Computer Science 2017-02-14 Dmitry Batenkov , Yaniv Romano , Michael Elad

We introduce a novel capacity measure 2sED for statistical models based on the effective dimension. The new quantity provably bounds the generalization error under mild assumptions on the model. Furthermore, simulations on standard data…

Machine Learning · Statistics 2025-07-03 Massimiliano Datres , Gian Paolo Leonardi , Alessio Figalli , David Sutter

We present a Bayesian approach to identify optimal transformations that map model input points to low dimensional latent variables. The "projection" mapping consists of an orthonormal matrix that is considered a priori unknown and needs to…

Machine Learning · Statistics 2021-09-22 Panagiotis Tsilifis , Piyush Pandita , Sayan Ghosh , Valeria Andreoli , Thomas Vandeputte , Liping Wang

The properties of flat minima in the empirical risk landscape of neural networks have been debated for some time. Increasing evidence suggests they possess better generalization capabilities with respect to sharp ones. First, we discuss…

The full-dimensional (metric, Euclidean, least squares) multidimensional scaling stress loss function is combined with a quadratic external penalty function term. The trajectory of minimizers of stress for increasing values of the penalty…

Computation · Statistics 2024-07-24 Jan de Leeuw