998 citations · 2.2k across the 70 of their papers we have counts for
7 papers · 1 filter
Stochastic Contextual Bandits with Long Horizon Rewards
Yuzhen Qin, Yingcong Li, Fabio Pasqualetti +2
The growing interest in complex decision-making and language modeling problems highlights the importance of sample-efficient learning over very long horizons. This work takes a ste…
Representation Learning for Context-Dependent Decision-Making
Yuzhen Qin, Tommaso Menara, Samet Oymak +2
Humans are capable of adjusting to changing environments flexibly and quickly. Empirical evidence has revealed that representation learning plays a crucial role in endowing humans…
Non-Stationary Representation Learning in Sequential Linear Bandits
Yuzhen Qin, Tommaso Menara, Samet Oymak +2
In this paper, we study representation learning for multi-task decision-making in non-stationary environments. We consider the framework of sequential linear bandits, where the age…
Robust Adversarial Classification via Abstaining
Abed AlRahman Al Makdah, Vaibhav Katewa, Fabio Pasqualetti
In this work, we consider a binary classification problem and cast it into a binary hypothesis testing framework, where the observations can be perturbed by an adversary. To improv…
Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustness
Abed AlRahman Al Makdah, Vishaal Krishnan, Fabio Pasqualetti
In this work, we propose a framework to learn feedback control policies with guarantees on closed-loop generalization and adversarial robustness. These policies are learned directl…
Lipschitz Bounds and Provably Robust Training by Laplacian Smoothing
Vishaal Krishnan, Abed AlRahman Al Makdah, Fabio Pasqualetti
In this work we propose a graph-based learning framework to train models with provable robustness to adversarial perturbations. In contrast to regularization-based approaches, we f…
A Fundamental Performance Limitation for Adversarial Classification
Abed AlRahman Al Makdah, Vaibhav Katewa, Fabio Pasqualetti
Despite the widespread use of machine learning algorithms to solve problems of technological, economic, and social relevance, provable guarantees on the performance of these data-d…