Andrew Jacobsen

Universita degli Studi di Milano & Politecnico di Milano

Papers on Lattice

Total citations

Topics

Research focus

Training Efficiency & Optimization (2)Natural Language Processing (1)Recommendation & Information Retrieval (1)

Frequent co-authors

Nicolò Cesa-Bianchi (2)Yuheng Zhao (1)Dorian Baudry (1)Shinji Ito (1)

Papers (2)

Apr 13, 2026

Apr 13, 2026·also PoliMi, Università degli Studi di Milano

Gradient-Variation Regret Bounds for Unconstrained Online Learning

Gradient variation, not just magnitude, unlocks tighter regret bounds in online learning, even without knowing problem parameters.

Yuheng Zhao, Andrew Jacobsen, Nicolò Cesa-Bianchi

Training Efficiency & Optimization

Mar 30, 2026

Mar 30, 2026·also Università degli Studi di Milano

A Perturbation Approach to Unconstrained Linear Bandits

Unconstrained bandit linear optimization can be surprisingly reduced to standard online linear optimization using a perturbation approach, unlocking new regret guarantees and high-probability bounds.

Andrew Jacobsen, Dorian Baudry, Shinji Ito +1

Natural Language Processing Recommendation & Information Retrieval Training Efficiency & Optimization

Search

Andrew Jacobsen

Research focus

Frequent co-authors

Papers (2)