activity
20242026
collaborators

11 papers

math.OC2026

AdaGrad does not adapt to Hölder-smoothness for composite objectives

Matia Bojovic, Saverio Salzo, Massimiliano Pontil

We exhibit a simple deterministic one-dimensional convex composite optimization problem for which AdaGrad scheme does not achieve the classical convergence rate $\mathcal{O}(n^{-(1…

math.OC2026

Bilevel learning

Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo +1

Bilevel learning refers to machine learning problems that can be formulated as bilevel optimization models, where decisions are organized in a hierarchical structure. This paradigm…

stat.ML2026

AdaGrad-Diff: A New Version of the Adaptive Gradient Algorithm

Matia Bojovic, Saverio Salzo, Massimiliano Pontil

Vanilla gradient methods are often highly sensitive to the choice of stepsize, which typically requires manual tuning. Adaptive methods alleviate this issue and have therefore beco…

stat.ML2025

Hyperparameter Optimization in Machine Learning

Luca Franceschi, Michele Donini, Valerio Perrone +5

Hyperparameters are configuration variables controlling the behavior of machine learning algorithms. They are ubiquitous in machine learning and artificial intelligence and the cho…

stat.ML2025

A conversion theorem and minimax optimality for continuum contextual bandits

Arya Akhavan, Karim Lounici, Massimiliano Pontil +1

We study the contextual continuum bandits problem, where the learner sequentially receives a side information vector and has to choose an action in a convex set, minimizing a funct…

cs.LG2025

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products

Julien Siems, Timur Carstensen, Arber Zela +3

Linear Recurrent Neural Networks (linear RNNs) have emerged as competitive alternatives to Transformers for sequence modeling, offering efficient training and linear-time inference…