8 papers · 1 filter
Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory
Hao Qiu, Andrew Jacobsen, Emmanuel Esposito +1
In this paper, we study dynamic regret in unconstrained online convex optimization (OCO) with movement costs. Specifically, we generalize the standard setting by allowing the movem…
Exploiting Curvature in Online Convex Optimization with Delayed Feedback
Hao Qiu, Emmanuel Esposito, Mengxiao Zhang
In this work, we study the online convex optimization problem with curved losses and delayed feedback. When losses are strongly convex, existing approaches obtain regret bounds of…
When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses
Antoine Moulin, Emmanuel Esposito, Dirk van der Hoeven
We consider the problem setting of prediction with expert advice with possibly heavy-tailed losses, i.e. the only assumption on the losses is an upper bound on their second moments…
Improved Regret Bounds for Bandits with Expert Advice
Nicolò Cesa-Bianchi, Khaled Eldowa, Emmanuel Esposito +1
In this research note, we revisit the bandits with expert advice problem. Under a restricted feedback model, we prove a lower bound of order for the worst-cas…
An Improved Uniform Convergence Bound with Fat-Shattering Dimension
Roberto Colomboni, Emmanuel Esposito, Andrea Paudice
The fat-shattering dimension characterizes the uniform convergence property of real-valued functions. The state-of-the-art upper bounds feature a multiplicative squared logarithmic…
Delayed Bandits: When Do Intermediate Observations Help?
Emmanuel Esposito, Saeed Masoudian, Hao Qiu +3
We study a -armed bandit with delayed feedback and intermediate observations. We consider a model where intermediate observations have a form of a finite state, which is observe…
On the Minimax Regret for Online Learning with Feedback Graphs
Khaled Eldowa, Emmanuel Esposito, Tommaso Cesari +1
In this work, we improve on the upper and lower bounds for the regret of online learning with strongly observable undirected feedback graphs. The best known upper bound for this pr…
Learning on the Edge: Online Learning with Stochastic Feedback Graphs
Emmanuel Esposito, Federico Fusco, Dirk van der Hoeven +1
The framework of feedback graphs is a generalization of sequential decision-making with bandit or full information feedback. In this work, we study an extension where the directed…