English
Related papers

Related papers: Achieving robustness in classification using optim…

200 papers

Designing neural networks with bounded Lipschitz constant is a promising way to obtain certifiably robust classifiers against adversarial examples. However, the relevant progress for the important $\ell_\infty$ perturbation setting is…

Machine Learning · Computer Science 2022-10-28 Bohang Zhang , Du Jiang , Di He , Liwei Wang

Recent studies on the adversarial vulnerability of neural networks have shown that models trained with the objective of minimizing an upper bound on the worst-case loss over all possible adversarial perturbations improve robustness against…

Machine Learning · Computer Science 2019-10-22 Anindya Sarkar , Nikhil Kumar Gupta , Raghu Iyengar

We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal.…

Machine Learning · Computer Science 2017-07-17 Miguel Á. Carreira-Perpiñán , Yerlan Idelbayev

We develop a theory of optimal transport relative to a distinguished subset, which acts as a reservoir of mass, allowing us to compare measures of different total variation. This relative transportation problem has an optimal solution and…

Metric Geometry · Mathematics 2026-04-08 Peter Bubenik , Alex Elchesen

Entropic optimal transport (OT) and the Sinkhorn algorithm have made it practical for machine learning practitioners to perform the fundamental task of calculating transport distance between statistical distributions. In this work, we focus…

Optimization and Control · Mathematics 2024-03-11 Xun Tang , Holakou Rahmanian , Michael Shavlovsky , Kiran Koshy Thekumparampil , Tesi Xiao , Lexing Ying

Capacity constrained optimal transport is a variant of optimal transport, which adds extra constraints on the set of feasible couplings in the original optimal transport problem to limit the mass transported between each pair of source and…

Optimization and Control · Mathematics 2025-02-13 Tianhao Wu , Qihao Cheng , Zihao Wang , Chaorui Zhang , Bo Bai , Zhongyi Huang , Hao Wu

The function that maps a family of probability measures to the solution of the dual entropic optimal transport problem is known as the Schr\"odinger map. We prove that when the cost function is $\mathcal{C}^{k+1}$ with $k\in \mathbb{N}^*$…

Optimization and Control · Mathematics 2024-03-04 Guillaume Carlier , Lénaïc Chizat , Maxime Laborde

We give a new proof of the Caffarelli contraction theorem, which states that the Brenier optimal transport map sending the standard Gaussian measure onto a uniformly log-concave probability measure is Lipschitz. The proof combines a recent…

Probability · Mathematics 2019-04-15 Max Fathi , Nathael Gozlan , Maxime Prodhomme

Learning conditional distributions is challenging because the desired outcome is not a single distribution but multiple distributions that correspond to multiple instances of the covariates. We introduce a novel neural entropic optimal…

Machine Learning · Computer Science 2024-06-05 Bao Nguyen , Binh Nguyen , Hieu Trung Nguyen , Viet Anh Nguyen

Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep learning community. Unfortunately, it has been shown both…

Machine Learning · Computer Science 2023-12-20 Stanislas Ducotterd , Alexis Goujon , Pakshal Bohra , Dimitris Perdios , Sebastian Neumayer , Michael Unser

This paper considers stochastic convex optimization problems with smooth functional constraints arising in constrained estimation and robust signal recovery. We operate in the high-dimensional and highly-constrained setting, where oracle…

Optimization and Control · Mathematics 2025-12-16 Vaibhav Rajoriya , Prateek Priyaranjan Pradhan , Ketan Rajawat

This paper introduces a new nonlinear dictionary learning method for histograms in the probability simplex. The method leverages optimal transport theory, in the sense that our aim is to reconstruct histograms using so-called displacement…

Making sense of Wasserstein distances between discrete measures in high-dimensional settings remains a challenge. Recent work has advocated a two-step approach to improve robustness and facilitate the computation of optimal transport, using…

Machine Learning · Computer Science 2019-09-04 François-Pierre Paty , Marco Cuturi

We consider the entropic regularization of discretized optimal transport and propose to solve its optimality conditions via a logarithmic Newton iteration. We show a quadratic convergence rate and validate numerically that the method…

Optimization and Control · Mathematics 2018-02-12 Christoph Brauer , Christian Clason , Dirk Lorenz , Benedikt Wirth

This paper presents a unified framework for smooth convex regularization of discrete optimal transport problems. In this context, the regularized optimal transport turns out to be equivalent to a matrix nearness problem with respect to…

Machine Learning · Statistics 2018-07-17 Arnaud Dessein , Nicolas Papadakis , Jean-Luc Rouas

We study Benamou's domain decomposition algorithm for optimal transport in the entropy regularized setting. The key observation is that the regularized variant converges to the globally optimal solution under very mild assumptions. We prove…

Optimization and Control · Mathematics 2021-11-23 Mauro Bonafini , Bernhard Schmitzer

We study unconstrained Online Linear Optimization with Lipschitz losses. Motivated by the pursuit of instance optimality, we propose a new algorithm that simultaneously achieves ($i$) the AdaGrad-style second order gradient adaptivity; and…

Machine Learning · Computer Science 2024-02-23 Zhiyu Zhang , Heng Yang , Ashok Cutkosky , Ioannis Ch. Paschalidis

We use distributionally-robust optimization for machine learning to mitigate the effect of data poisoning attacks. We provide performance guarantees for the trained model on the original data (not including the poison records) by training…

Machine Learning · Computer Science 2020-01-30 Farhad Farokhi

We propose a non-parametric variant of binary regression, where the hypothesis is regularized to be a Lipschitz function taking a metric space to [0,1] and the loss is logarithmic. This setting presents novel computational and statistical…

Machine Learning · Computer Science 2020-10-21 Ariel Avital , Klim Efremenko , Aryeh Kontorovich , David Toplin , Bo Waggoner

We compare several approaches to learn an Optimal Map, represented as a neural network, between probability distributions. The approaches fall into two categories: ``Heuristics'' and approaches with a more sound mathematical justification,…

Machine Learning · Computer Science 2019-08-06 Andrea Schioppa
‹ Prev 1 4 5 6 7 8 10 Next ›