English
Related papers

Related papers: Almost-Orthogonal Layers for Efficient General-Pur…

200 papers

We consider the problem of training a deep orthogonal linear network, which consists of a product of orthogonal matrices, with no non-linearity in-between. We show that training the weights with Riemannian gradient descent is equivalent to…

Machine Learning · Statistics 2020-11-30 Pierre Ablin

We initiate the study of numerical linear algebra in the sliding window model, where only the most recent $W$ updates in a stream form the underlying data set. We first introduce a unified row-sampling based framework that gives randomized…

Data Structures and Algorithms · Computer Science 2023-04-12 Vladimir Braverman , Petros Drineas , Cameron Musco , Christopher Musco , Jalaj Upadhyay , David P. Woodruff , Samson Zhou

Optical satellite-to-ground communication (OSGC) has the potential to improve access to fast and affordable Internet in remote regions. Atmospheric turbulence, however, distorts the optical beam, eroding the data rate potential when…

Machine Learning · Computer Science 2023-03-15 Payam Parvizi , Runnan Zou , Colin Bellinger , Ross Cheriton , Davide Spinello

We introduce in this paper an optimal first-order method that allows an easy and cheap evaluation of the local Lipschitz constant of the objective's gradient. This constant must ideally be chosen at every iteration as small as possible,…

Optimization and Control · Mathematics 2012-07-18 Michel Baes , Michael Buergisser

Lipschitz continuity of algorithms, introduced by Kumabe and Yoshida (FOCS'23), measures the stability of an algorithm against small input perturbations. Algorithms with small Lipschitz continuity are desirable, as they ensure reliable…

Data Structures and Algorithms · Computer Science 2025-07-01 Tatsuya Gima , Soh Kumabe , Yuichi Yoshida

We study a class of optimization problems on Riemannian manifolds, where the objective function consists of a smooth term and quasi-norm type penalties with exponent $p \in (0, 1]$. The essential difficulty lies in the fact that the…

Optimization and Control · Mathematics 2026-04-21 Lei Wang , Xiaojun Chen

This paper is concerned with the training of neural networks (NNs) under semidefinite constraints, which allows for NN training with robustness and stability guarantees. In particular, we focus on Lipschitz bounds for NNs. Exploiting the…

Machine Learning · Computer Science 2022-09-21 Patricia Pauli , Niklas Funcke , Dennis Gramlich , Mohamed Amine Msalmi , Frank Allgöwer

We present a framework for performing efficient regression in general metric spaces. Roughly speaking, our regressor predicts the value at a new point by computing a Lipschitz extension --- the smoothest function consistent with the…

Machine Learning · Computer Science 2017-04-25 Lee-Ad Gottlieb , Aryeh Kontorovich , Robert Krauthgamer

This paper deals with an optimization problem over a network of agents, where the cost function is the sum of the individual objectives of the agents and the constraint set is the intersection of local constraints. Most existing methods…

Optimization and Control · Mathematics 2018-06-20 Van Sy Mai , Eyad H. Abed

Robust topological information commonly comes in the form of a set of persistence diagrams, finite measures that are in nature uneasy to affix to generic machine learning frameworks. We introduce a fast, learnt, unsupervised vectorization…

Computational Geometry · Computer Science 2020-10-16 Martin Royer , Frédéric Chazal , Clément Levrard , Umeda Yuhei , Ike Yuichi

In this work, we consider the distributed optimization of non-smooth convex functions using a network of computing units. We investigate this problem under two regularity assumptions: (1) the Lipschitz continuity of the global objective…

Optimization and Control · Mathematics 2018-06-04 Kevin Scaman , Francis Bach , Sébastien Bubeck , Yin Tat Lee , Laurent Massoulié

We study the problem of inferring a sparse vector from random linear combinations of its components. We propose the Accelerated Orthogonal Least-Squares (AOLS) algorithm that improves performance of the well-known Orthogonal Least-Squares…

Machine Learning · Statistics 2018-04-17 Abolfazl Hashemi , Haris Vikalo

Deep neural networks have shown remarkable performance across a wide range of vision-based tasks, particularly due to the availability of large-scale datasets for training and better architectures. However, data seen in the real world are…

Machine Learning · Computer Science 2018-11-26 Muhammad Usama , Dong Eui Chang

Despite the large success of deep neural networks (DNN) in recent years, most neural networks still lack mathematical guarantees in terms of stability. For instance, DNNs are vulnerable to small or even imperceptible input perturbations, so…

Machine Learning · Computer Science 2022-11-02 Leon Bungert , René Raab , Tim Roith , Leo Schwinn , Daniel Tenbrinck

Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints.…

Machine Learning · Computer Science 2025-11-26 Shaharyar Ahmed Khan Tareen , Filza Khan Tareen

Sampling from generative models has become a crucial tool for applications like data synthesis and augmentation. Diffusion, Flow Matching and Continuous Normalising Flows have shown effectiveness across various modalities, and rely on…

Machine Learning · Statistics 2025-11-10 Erik Bodin , Alexandru Stere , Dragos D. Margineantu , Carl Henrik Ek , Henry Moss

To improve detection robustness in adverse conditions (e.g., haze and low light), image restoration is commonly applied as a pre-processing step to enhance image quality for the detector. However, the functional mismatch between restoration…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Qing Zhao , Weijian Deng , Pengxu Wei , ZiYi Dong , Hannan Lu , Xiangyang Ji , Liang Lin

The aim of this paper is twofold. First, we show that a certain concatenation of a proximity operator with an affine operator is again a proximity operator on a suitable Hilbert space. Second, we use our findings to establish so-called…

Self-organization of robust and efficient networks is important for a future design of communication or transportation systems, because both characteristics are not coexisting in many real networks. As one of the candidates for the…

Physics and Society · Physics 2022-06-15 Fuxuan Liao , Yukio Hayashi

The Jacobian matrix (or the gradient for single-output networks) is directly related to many important properties of neural networks, such as the function landscape, stationary points, (local) Lipschitz constants and robustness to…

Machine Learning · Statistics 2019-02-28 Huan Zhang , Pengchuan Zhang , Cho-Jui Hsieh