Sequential information design: Learning to persuade in the dark

M Bernasconi, M Castiglioni… - Advances in …, 2022 - proceedings.neurips.cc
We study a repeated information design problem faced by an informed sender who tries to
influence the behavior of a self-interested receiver. We consider settings where the receiver …

Safe Linear Bandits over Unknown Polytopes

A Gangrade, T Chen… - The Thirty Seventh Annual …, 2024 - proceedings.mlr.press
The safe linear bandit problem (SLB) is an online approach to linear programming with
unknown objective and unknown\emph {roundwise} constraints, under stochastic bandit …

Achieving Regular and Fair Learning in Combinatorial Multi-Armed Bandit

X Wu, B Li - IEEE INFOCOM 2024-IEEE Conference on …, 2024 - ieeexplore.ieee.org
Combinatorial multi-armed bandit refers to the model that aims to maximize cumulative
rewards in the presence of uncertainty. Motivated by two important wireless network …

Learning Adversarial MDPs with Stochastic Hard Constraints

FE Stradi, M Castiglioni, A Marchesi, N Gatti - arxiv preprint arxiv …, 2024 - arxiv.org
We study online learning problems in constrained Markov decision processes (CMDPs) with
adversarial losses and stochastic hard constraints. We consider two different scenarios. In …

Machine learning to optimize additive manufacturing for visible photonics

A Lininger, A Aththanayake, J Boyd, O Ali, M Goel… - …, 2023 - degruyter.com
Additive manufacturing has become an important tool for fabricating advanced systems and
devices for visible nanophotonics. However, the lack of simulation and optimization methods …

Online learning in sequential Bayesian persuasion: Handling unknown priors

M Bernasconi, M Castiglioni, A Marchesi, N Gatti… - Artificial Intelligence, 2025 - Elsevier
We study a repeated information design problem faced by an informed sender who tries to
influence the behavior of a self-interested receiver, through the provision of payoff-relevant …

Doubly-Optimistic Play for Safe Linear Bandits

T Chen, A Gangrade, V Saligrama - arxiv preprint arxiv:2209.13694, 2022 - arxiv.org
The safe linear bandit problem (SLB) is an online approach to linear programming with
unknown objective and unknown round-wise constraints, under stochastic bandit feedback …

A General Framework for Safe Decision Making: A Convex Duality Approach

M Bernasconi, F Cacciamani, N Gatti… - NeurIPS ML Safety …, 2022 - openreview.net
We study the problem of online interaction in general decision making problems, where the
objective is not only to find optimal strategies, but also to satisfy some safety guarantees …

Constrained learning in the bandit setting: doubly optimistic strategies and fast rates

T Chen - 2024 - open.bu.edu
The (stochastic) bandit problem is a classic example used to address the challenge of
balancing exploration and exploitation when dealing with bandit feedback. This dissertation …

Online learning in CMDPs with adversarial losses and stochastic hard constraints

FE Stradi, M Castiglioni, A Marchesi, N Gatti - … European Workshop on … - openreview.net
We study online learning in constrained Markov decision processes (CMDPs) with
adversarial losses and stochastic hard constraints, under bandit feedback. We consider two …