English
Related papers

Related papers: Representing smooth functions as compositions of n…

200 papers

The local Lipschitz constant of a neural network is a useful metric with applications in robustness, generalization, and fairness evaluation. We provide novel analytic results relating the local Lipschitz constant of nonsmooth vector-valued…

Machine Learning · Statistics 2021-01-12 Matt Jordan , Alexandros G. Dimakis

We prove that every continuous function on a separable infinite-dimensional Hilbert space X can be uniformly approximated by smooth functions with no critical points. This kind of result can be regarded as a sort of very strong approximate…

Differential Geometry · Mathematics 2007-05-23 Daniel Azagra , Manuel Cepedello Boiso

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

We represent minimal upper gradients of Newtonian functions, in the range $1\le p<\infty$, by maximal directional derivatives along "generic" curves passing through a given point, using plan-modulus duality and disintegration techniques. As…

Metric Geometry · Mathematics 2024-03-13 Sylvester Eriksson-Bique , Elefterios Soultanis

We consider high order approximations of the solution of the stochastic filtering problem, derive their pathwise representation in the spirit of the earlier work of Clark and Davis and prove their robustness property. In particular, we show…

Numerical Analysis · Mathematics 2021-01-12 Dan Crisan , Alexander Lobbe , Salvador Ortiz-Latorre

For any scalar-valued bivariate function that is locally Lipschitz continuous and directionally differentiable, it is shown that a subgradient may always be constructed from the function's directional derivatives in the four compass…

Optimization and Control · Mathematics 2023-06-22 Kamil A. Khan , Yingwei Yuan

Lipschitz constants of neural networks allow for guarantees of robustness in image classification, safety in controller design, and generalizability beyond the training data. As calculating Lipschitz constants is NP-hard, techniques for…

Machine Learning · Computer Science 2024-01-09 Anton Xue , Lars Lindemann , Alexander Robey , Hamed Hassani , George J. Pappas , Rajeev Alur

In this paper we investigate the approximation of continuous functions on the Wasserstein space by smooth functions, with smoothness meant in the sense of Lions differentiability. In particular, in the case of a Lipschitz function we are…

Probability · Mathematics 2023-08-14 Andrea Cosso , Mattia Martini

We generalize the notion of average Lipschitz smoothness proposed by Ashlagi et al. (COLT 2021) by extending it to H\"older smoothness. This measure of the "effective smoothness" of a function is sensitive to the underlying distribution and…

Machine Learning · Computer Science 2023-10-31 Steve Hanneke , Aryeh Kontorovich , Guy Kornowski

One means of fitting functions to high-dimensional data is by providing smoothness constraints. Recently, the following smooth function approximation problem was proposed: given a finite set $E \subset \mathbb{R}^d$ and a function $f: E…

Machine Learning · Statistics 2018-04-02 Adam Gustafson , Matthew Hirn , Kitty Mohammed , Hariharan Narayanan , Jason Xu

Deep residual networks (ResNets) have demonstrated outstanding success in computer vision tasks, attributed to their ability to maintain gradient flow through deep architectures. Simultaneously, controlling the Lipschitz bound in neural…

Machine Learning · Computer Science 2025-03-03 Marius F. R. Juston , William R. Norris , Dustin Nottage , Ahmet Soylemezoglu

In this paper, we address stochastic optimization problems involving a composition of a non-smooth outer function and a smooth inner function, a formulation frequently encountered in machine learning and operations research. To deal with…

Optimization and Control · Mathematics 2026-05-15 Tommaso Giovannelli , Jingfu Tan , Luis Nunes Vicente

We study the connection between the highly non-convex loss function of a simple model of the fully-connected feed-forward neural network and the Hamiltonian of the spherical spin-glass model under the assumptions of: i) variable…

Machine Learning · Computer Science 2015-01-23 Anna Choromanska , Mikael Henaff , Michael Mathieu , Gérard Ben Arous , Yann LeCun

We study a method for calculating the utility function from a candidate of a demand function that is not differentiable, but is locally Lipschitz. Using this method, we obtain two new necessary and sufficient conditions for a candidate of a…

Theoretical Economics · Economics 2024-04-02 Yuhki Hosoya

We introduce LiPopt, a polynomial optimization framework for computing increasingly tighter upper bounds on the Lipschitz constant of neural networks. The underlying optimization problems boil down to either linear (LP) or semidefinite…

Machine Learning · Computer Science 2020-04-21 Fabian Latorre , Paul Rolland , Volkan Cevher

This paper investigates a category of constrained fractional optimization problems that emerge in various practical applications. The objective function for this category is characterized by the ratio of a numerator and denominator, both…

Optimization and Control · Mathematics 2026-05-28 Yizun Lin , Jian-Feng Cai , Zhao-Rong Lai , Cheng Li

Subgradient methods comprise a fundamental class of nonsmooth optimization algorithms. Classical results show that certain subgradient methods converge sublinearly for general Lipschitz convex functions and converge linearly for convex…

Optimization and Control · Mathematics 2022-01-13 Vasileios Charisopoulos , Damek Davis

We consider a composite optimization problem where the sum of a continuously differentiable and a merely lower semicontinuous function has to be minimized. The proximal gradient algorithm is the classical method for solving such a problem…

Optimization and Control · Mathematics 2023-05-01 Xiaoxi Jia , Christian Kanzow , Patrick Mehlitz

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

Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by computing a global bound on its Lipschitz constant.…

Machine Learning · Computer Science 2021-11-03 Yujia Huang , Huan Zhang , Yuanyuan Shi , J Zico Kolter , Anima Anandkumar