Ufuk Topcu

TL;DR: In this article, the authors leverage ideas from compressive sensing to generate random feature expansions with theoretical guarantees even in the data-scarce setting, and provide generalization bounds for functions in a certain class (that is dense in a reproducing kernel Hilbert space).

TL;DR: A policy search algorithm that employs online mirror descent using an optimistically biased estimator of the loss function is proposed and it is proved that the proposed algorithm achieves both on expectation and with high probability a sublinear regret of $\tilde{\mathcal{O}}(\sqrt{L T\vert\Mathcal{S}\Vert \mathcal {A}\vert})$.

TL;DR: This work considers a scenario in which a group of agents aim to collectively transmit a message signal to a client through beamforming and develops two greedy algorithms and a difference-of-submodular algorithm which returns a locally optimal solution to a certain relaxation of the subset selection problem regardless of the maximum localization error.

TL;DR: A new optimization criterion for MDP policies that captures the task of working towards the satisfaction of some infinite-time horizon ω-regular specification is introduced and it is given an algorithm to compute policies that are optimal in this criterion and it captures the ideas of optimism and risk-averseness in MDP control.

TL;DR: A post-training privacy-protection algorithm that adds noise to the neural network’s weights and a novel differential privacy mechanism that samples noise from the logistic distribution is designed.