Handling Hard Affine SDP Shape Constraints in RKHSs

01/05/2021
by   Pierre-Cyril Aubin-Frankowski, et al.
0

Shape constraints, such as non-negativity, monotonicity, convexity or supermodularity, play a key role in various applications of machine learning and statistics. However, incorporating this side information into predictive models in a hard way (for example at all points of an interval) for rich function classes is a notoriously challenging problem. We propose a unified and modular convex optimization framework, relying on second-order cone (SOC) tightening, to encode hard affine SDP constraints on function derivatives, for models belonging to vector-valued reproducing kernel Hilbert spaces (vRKHSs). The modular nature of the proposed approach allows to simultaneously handle multiple shape constraints, and to tighten an infinite number of constraints into finitely many. We prove the consistency of the proposed scheme and that of its adaptive variant, leveraging geometric properties of vRKHSs. The efficiency of the approach is illustrated in the context of shape optimization, safety-critical control and econometrics.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 29

05/26/2020

Hard Shape-Constrained Kernel Machines

Shape constraints (such as non-negativity, monotonicity, convexity) play...
05/31/2021

Control Occupation Kernel Regression for Nonlinear Control-Affine Systems

This manuscript presents an algorithm for obtaining an approximation of ...
03/21/2020

A level set representation method for N-dimensional convex shape and applications

In this work, we present a new efficient method for convex shape represe...
03/29/2021

Event-Triggered Safety-Critical Control for Systems with Unknown Dynamics

This paper addresses the problem of safety-critical control for systems ...
02/18/2016

Efficient approaches for escaping higher order saddle points in non-convex optimization

Local search heuristics for non-convex optimizations are popular in appl...
05/07/2019

Sparse multiresolution representations with adaptive kernels

Reproducing kernel Hilbert spaces (RKHSs) are key elements of many non-p...
10/29/2020

Compensating data shortages in manufacturing with monotonicity knowledge

We present a regression method for enhancing the predictive power of a m...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.