Tukey Depths and Hamilton-Jacobi Differential Equations

04/04/2021
by   Martin Molina-Fructuoso, et al.
0

The widespread application of modern machine learning has increased the need for robust statistical algorithms. This work studies one such fundamental statistical measure known as the Tukey depth. We study the problem in the continuum (population) limit. In particular, we derive the associated necessary conditions, which take the form of a first-order partial differential equation. We discuss the classical interpretation of this necessary condition as the viscosity solution of a Hamilton-Jacobi equation, but with a non-classical Hamiltonian with discontinuous dependence on the gradient at zero. We prove that this equation possesses a unique viscosity solution and that this solution always bounds the Tukey depth from below. In certain cases, we prove that the Tukey depth is equal to the viscosity solution, and we give some illustrations of standard numerical methods from the optimal control community which deal directly with the partial differential equation. We conclude by outlining several promising research directions both in terms of new numerical algorithms and theoretical challenges.

READ FULL TEXT

page 26

page 28

page 29

research
03/26/2020

Learning To Solve Differential Equations Across Initial Conditions

Recently, there has been a lot of interest in using neural networks for ...
research
06/01/2023

Wavefront reconstruction of discontinuous phase objects from optical deflectometry

One of the challenges in phase measuring deflectometry is to retrieve th...
research
10/15/2022

Well-definedness of Physical Law Learning: The Uniqueness Problem

Physical law learning is the ambiguous attempt at automating the derivat...
research
05/21/2018

The limit shape of convex hull peeling

We prove that the convex peeling of a random point set in dimension d ap...
research
11/21/2020

Adversarial Classification: Necessary conditions and geometric flows

We study a version of adversarial classification where an adversary is e...
research
04/25/2020

Numerical Solution of the Parametric Diffusion Equation by Deep Neural Networks

We perform a comprehensive numerical study of the effect of approximatio...
research
09/14/2021

A fast, high-order numerical method for the simulation of single-excitation states in quantum optics

We consider the numerical solution of a nonlocal partial differential eq...

Please sign up or login with your details

Forgot password? Click here to reset