Skip to Main content Skip to Navigation

Handling Hard Affine SDP Shape Constraints in RKHSs

Abstract : 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.
Complete list of metadata
Contributor : Zoltan Szabo <>
Submitted on : Tuesday, January 5, 2021 - 5:50:14 PM
Last modification on : Thursday, January 28, 2021 - 3:08:32 AM
Long-term archiving on: : Wednesday, April 7, 2021 - 9:30:07 AM


Files produced by the author(s)


  • HAL Id : hal-03098495, version 1


Pierre-Cyril Aubin-Frankowski, Zoltán Szabó. Handling Hard Affine SDP Shape Constraints in RKHSs. [Research Report] MINES ParisTech; Ecole Polytechnique. 2021. ⟨hal-03098495⟩



Record views


Files downloads