activity
20242026
collaborators

7 papers

math.OC2026

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…

math.OC2026

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…

cs.LG2025

When majority rules, minority loses: bias amplification of gradient descent

François Bachoc, Jérôme Bolte, Ryan Boustany +1

Despite growing empirical evidence of bias amplification in machine learning, its theoretical foundations remain poorly understood. We develop a formal framework for majority-minor…

cs.LG2025

Convergence of optimizers implies eigenvalues filtering at equilibrium

Jerome Bolte, Quoc-Tung Le, Edouard Pauwels

Ample empirical evidence in deep neural network training suggests that a variety of optimizers tend to find nearly global optima. In this article, we adopt the reversed perspective…

math.OC2025

Inexact subgradient methods for semialgebraic functions

Jérôme Bolte, Tam Le, Éric 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…

cs.CC2025

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…