7 papers
The adjoint state method for parametric definable optimization without smoothness or uniqueness
Jérôme Bolte, Edouard Pauwels, Cheik Traoré
We establish that nonconvex definable parametric optimization problems with possibly nonsmooth objectives, inequality constraints, conic constraint systems, and non-unique primal a…
Bilevel gradient methods and the Morse parametric qualification condition
Jérôme Bolte, Quoc-Tung Le, Edouard Pauwels +1
We introduce the Morse parametric qualification condition for bilevel programming. Generic semi-algebraic functions are Morse parametric in a piecewise sense. Thus, bilevel program…
Learning Theory for Kernel Bilevel Optimization
Fares El Khoury, Edouard Pauwels, Samuel Vaiter +1
Bilevel optimization has emerged as a technique for addressing a wide range of machine learning problems that involve an outer objective implicitly determined by the minimizer of a…
Inexact subgradient methods for semialgebraic functions
Jérôme Bolte, Tam Le, Ãric Moulines +1
Motivated by the extensive application of approximate gradients in machine learning and optimization, we investigate inexact subgradient methods subject to persistent additive erro…
Geometric and computational hardness of bilevel programming
Jérôme Bolte, Quoc-Tung Le, Edouard Pauwels +1
We first show a simple but striking result in bilevel optimization: unconstrained smooth bilevel programming is as hard as general extended-real-valued lower semicontinu…
A second-order-like optimizer with adaptive gradient scaling for deep learning
Jérôme Bolte, Ryan Boustany, Edouard Pauwels +1
In this empirical article, we introduce INNAprop, an optimization algorithm that combines the INNA method with the RMSprop adaptive gradient scaling. It leverages second-order info…