10 papers
Langevin for Nonconvex Optimization: Exact, Inexact and Zeroth-Order
Emanuele Naldi, Marco Rando, Lorenzo Rosasco +1
We study Langevin-based methods for non-convex optimization under smoothness and dissipativity assumptions. Our focus is on obtaining non-asymptotic bounds for the expected excess…
Smart strategies to navigate turbulent odor plumes reorienting to local wind
Lorenzo Piro, Maurizio Carbone, Luca Biferale +4
Olfactory search in turbulent environments is a sensorimotor problem that many animals solve with remarkable efficiency, yet replicating this ability in artificial systems is an en…
Clock-state olfactory search in turbulent flows using Q-learning: The geometry of plume recovery
Marco Rando, Robin A. Heinonen, Yujia Qi +1
Finding an odor source in a turbulent flow requires effectively leveraging the history of olfactory observations into a robust navigation strategy. In this work, we use tabular Q-l…
On the Hardness of Junking LLMs
Marco Rando, Samuel Vaiter
Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attac…
ZOBA: An Efficient Single-loop Zeroth-order Bilevel Optimization Algorithm
Marco Rando, Samuel Vaiter
Bilevel optimization problems consist of minimizing a value function whose evaluation depends on the solution of an inner optimization problem. These problems are typically tackled…
A New Formulation for Zeroth-Order Optimization of Adversarial EXEmples in Malware Detection
Marco Rando, Luca Demetrio, Lorenzo Rosasco +1
Machine learning malware detectors are vulnerable to adversarial EXEmples, i.e., carefully-crafted Windows programs tailored to evade detection. Unlike other adversarial problems,…