English
Related papers

Related papers: Random Parametrization Double Tensors Integrals an…

200 papers

Recent theoretical work has established connections between over-parametrized neural networks and linearized models governed by he Neural Tangent Kernels (NTKs). NTK theory leads to concrete convergence and generalization results, yet the…

Machine Learning · Computer Science 2020-02-18 Yu Bai , Jason D. Lee

In this paper we implement for the first time the use of a {\pi}N{\Delta}(1232) vertex interaction containing both first and second order derivative terms, as required by renormalization considerations. As as was previously shown both…

High Energy Physics - Phenomenology · Physics 2019-08-07 Alejandro Mariano , Daniel Badagnani , Cesar Barbero

Chebyshev's inequality provides an upper bound on the tail probability of a random variable based on its mean and variance. While tight, the inequality has been criticized for only being attained by pathological distributions that abuse the…

Optimization and Control · Mathematics 2020-10-16 Ernst Roos , Ruud Brekelmans , Wouter van Eekelen , Dick den Hertog , Johan van Leeuwaarden

We obtain estimates for the Kolmogorov distance to appropriately chosen gaussians, of linear functions \[ \sum_{i\in [n]^d} \theta_i X_i \] of random tensors $\boldsymbol{X}=\langle X_i:i\in [n]^d\rangle$ which are symmetric and…

Probability · Mathematics 2023-09-12 Pandelis Dodos , Konstantinos Tyros

Approximating a tensor in the tensor train (TT) format has many important applications in scientific computing. Rounding a TT tensor involves further compressing a tensor that is already in the TT format. This paper proposes new randomized…

This work introduces the minimax Laplace transform method, a modification of the cumulant-based matrix Laplace transform method developed in "User-friendly tail bounds for sums of random matrices" (arXiv:1004.4389v6) that yields both upper…

Probability · Mathematics 2011-07-22 Alex Gittens , Joel A. Tropp

Hard-threshold estimators are popular in signal processing applications. We provide a detailed study of using hard-threshold estimators for estimating an unknown deterministic signal when additive white Gaussian noise corrupts observations.…

Statistics Theory · Mathematics 2008-01-24 Baris I. Erkmen , Vivek K. Goyal

Determinantal Point Processes (DPPs) are probabilistic models that arise in quantum physics and random matrix theory and have recently found numerous applications in computer science. DPPs define distributions over subsets of a given ground…

Data Structures and Algorithms · Computer Science 2017-04-25 L. Elisa Celis , Amit Deshpande , Tarun Kathuria , Damian Straszak , Nisheeth K. Vishnoi

Symmetry in the parameter space of deep neural networks (DNNs) has proven beneficial for various deep learning applications. A well-known example is the permutation symmetry in Multi-Layer Perceptrons (MLPs), where permuting the rows of…

Machine Learning · Computer Science 2025-05-30 Binchi Zhang , Zaiyi Zheng , Zhengzhang Chen , Jundong Li

Isogeometric Analysis is a variant of the finite element method, where spline functions are used for the representation of both the geometry and the solution. Splines, particularly those with higher degree, achieve their full approximation…

Numerical Analysis · Mathematics 2025-10-10 Stefan Takacs , Stefan Tyoler

Purpose: Magnetic polarizability tensors (MPTs) provide an economical characterisation of conducting magnetic metallic objects and their spectral signature can aid in the solution of metal detection inverse problems, such as scrap metal…

Numerical Analysis · Mathematics 2024-05-01 James Elgy , Paul D. Ledger

Calculating perturbation response properties of materials from first principles provides a vital link between theory and experiment, but is bottlenecked by the high computational cost. Here a general framework is proposed to perform density…

Computational Physics · Physics 2024-03-01 He Li , Zechen Tang , Jingheng Fu , Wen-Han Dong , Nianlong Zou , Xiaoxun Gong , Wenhui Duan , Yong Xu

Low-rank pseudoinverses are widely used to approximate matrix inverses in scalable machine learning, optimization, and scientific computing. However, real-world matrices are often observed with noise, arising from sampling, sketching, and…

Machine Learning · Computer Science 2025-10-30 Phuc Tran , Nisheeth K. Vishnoi

Matrix concentration inequalities, intimately connected to the Non-Commutative Khintchine inequality, have been an important tool in both applied and pure mathematics. We study tensor versions of these inequalities, and establish…

Probability · Mathematics 2024-11-19 Afonso S. Bandeira , Sivakanth Gopi , Haotian Jiang , Kevin Lucca , Thomas Rothvoss

In this paper, we propose a novel model to recover a low-rank tensor by simultaneously performing double nuclear norm regularized low-rank matrix factorizations to the all-mode matricizations of the underlying tensor. An block successive…

Computer Vision and Pattern Recognition · Computer Science 2020-05-07 Haijin Zeng , Xiaozhen Xie , Jifeng Ning

Data-processing inequalities capture the phenomenon that two probability distributions can only become less distinguishable under any common post-processing. For more fine-grained inequalities, one turns to strong data-processing inequality…

Quantum Physics · Physics 2026-05-08 Matthew Simon Tan , Marco Tomamichel , Ian George

An algorithm of improving the performance of iterative decoding on perpendicular magnetic recording is presented. This algorithm follows on the authors' previous works on the parallel and serial concatenated turbo codes and low-density…

Information Theory · Computer Science 2007-07-13 E. Papagiannis , C. Tjhai , M. Ahmed , M. Ambroze , M. Tomlinson

Unraveling the reasons behind the remarkable success and exceptional generalization capabilities of deep neural networks presents a formidable challenge. Recent insights from random matrix theory, specifically those concerning the spectral…

Machine Learning · Statistics 2023-04-10 Xuanzhe Xiao , Zeng Li , Chuanlong Xie , Fengwei Zhou

Tight bounds for several symmetric divergence measures are derived in terms of the total variation distance. It is shown that each of these bounds is attained by a pair of 2 or 3-element probability distributions. An application of these…

Information Theory · Computer Science 2016-11-17 Igal Sason

Let $X$ be an $n\times n$ symmetric random matrix with independent but non-identically distributed entries. The deviation inequalities of the spectral norm of $X$ with Gaussian entries have been obtained by using the standard concentration…

Probability · Mathematics 2023-08-22 Guozheng Dai , Zhonggen Su , Hanchao Wang
‹ Prev 1 3 4 5 6 7 10 Next ›