Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time
The 40th Conference on Neural Information Processing Systems, NeurIPS 2026, Sydney, Australia
Read paperFrancesco Emanuele Stradi
Postdoctoral Researcher
Politecnico di Milano
Research interests
Machine Learning Theory
Online Learning
Algorithmic Game Theory
01 / ABOUT
A little background.
I am a postdoc at the Department of Electronics, Information and Bioengineering (DEIB) at Politecnico di Milano, where I work with Prof. Alberto Marchesi.
I received my PhD in computer science at Politecnico di Milano, advised by Prof. Nicola Gatti. During my PhD, I was a visiting researcher at the Industrial Engineering & Operations Research (IEOR) Department at Columbia University, where I worked with Prof. Christian Kroer.
My research focuses on the theoretical aspects of artificial intelligence and online learning. I combine online learning theory with optimization techniques to build strategic agents that can act in complex online environments.
02 / RESEARCH
Publications.
2026
Multi-Armed Bandits With Best-Action Queries
The 40th Conference on Neural Information Processing Systems, NeurIPS 2026, Sydney, Australia
Read paperOnline Resource Allocation With General Constraints
The 40th Conference on Neural Information Processing Systems, NeurIPS 2026, Sydney, Australia
Read paperReplicable Constrained Bandits
The 40th Conference on Neural Information Processing Systems, NeurIPS 2026, Sydney, Australia
Read paperTruly Adapting to Adversarial Constraints in Constrained MABs
The 39th Annual Conference on Learning Theory, COLT 2026, San Diego, USA
Read paperPolicy Optimization for CMDPs with Bandit Feedback: Best-of-Both-Worlds and Beyond
Artificial Intelligence, 2026
Read paper2025
No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
The 39th Conference on Neural Information Processing Systems, NeurIPS 2025, San Diego, USA
Read paperData-Dependent Regret Bounds for Constrained MABs
The 39th Conference on Neural Information Processing Systems, NeurIPS 2025, San Diego, USA
Read paperTaming Adversarial Constraints in CMDPs
The 39th Conference on Neural Information Processing Systems, NeurIPS 2025, San Diego, USA
Read paperMarkov Persuasion Processes: Learning to Persuade From Scratch
The 39th Conference on Neural Information Processing Systems, NeurIPS 2025, San Diego, USA
Read paperLearning Adversarial MDPs with Stochastic Hard Constraints
The 42nd International Conference on Machine Learning, ICML 2025, Vancouver, Canada
Read paperPolicy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
The 42nd International Conference on Machine Learning, ICML 2025, Vancouver, Canada
Read paperOptimal Strong Regret and Violation in Constrained MDPs via Policy Optimization
The 13th International Conference on Learning Representations, ICLR 2025, Singapore, Singapore
Read paper2024
Bandits with Ranking Feedback
The 38th Conference on Neural Information Processing Systems, NeurIPS 2024, Vancouver, Canada
Read paperOnline Learning in CMDPs: Handling Stochastic and Adversarial Constraints
The 41st International Conference on Machine Learning, ICML 2024, Vienna, Austria
Read paperOnline Learning with Off-Policy Feedback in Adversarial MDPs
The 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju Island, South Korea
Read paperOnline Markov Decision Processes Configuration with Continuous Decision Space
The 38th AAAI Conference on Artificial Intelligence, AAAI 2024, Vancouver, Canada
Read paper03 / TEACHING
In the classroom.
Probabilità e Statistica Matematica
B.Sc. in Management Engineering
Statistica
B.Sc. in Mechanical Engineering