Scholar
Alberto Rumi
Google Scholar ID: sGVBi7UAAAAJ
PhD Student - University of Milan, CENTAI
Multi-Armed bandits
Online Learning
Reinforcement Learning
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
16
H-index
3
i10-index
1
Publications
5
Co-authors
0
Publications
3 items
BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment
2026
Cited
0
Parameter-Free Dynamic Regret for Unconstrained Linear Bandits
2026
Cited
0
Stochastic Shortest Path with Sparse Adversarial Costs
2025
Cited
0
