A selection of recent talks, with slides and recordings where available.
Talks
-
Beyond Strict Complementarity: A Variational Analysis Approach to Hyperparameter Optimization
Bilevel Optimization Society Webinar
Online · September 2026
Choosing one regularization weight per feature is a bilevel program with a nonsmooth lower level and thousands of upper-level variables. The standard hypergradient — implicit differentiation on the active support — assumes strict complementarity, and…
slides video -
Structured Strategies for Nonsmooth Bilevel Hyperparameter Optimization
SIAM Optimization
Edinburgh, UK · June 2026
This talk focuses on large-scale bilevel optimization problems that exhibit a natural block-separable structure, a setting that frequently appears in modern machine learning pipelines, large data-cleaning tasks, and parametric model selection. Such p…
slides -
Bilevel Hyperparameter Learning for Nonsmooth Regularized Imaging and Machine Learning Models
Applied Inverse Problems
Rio de Janeiro, Brazil · August 2025
We study a bilevel optimization framework for hyperparameter tuning of variational models, with a focus on sparse regression and classification tasks. In particular, we consider a weighted elastic-net regularizer, where feature-wise regularization pa…
slides