Aristotelis-Angelos Papadopoulos

TL;DR: A novel loss function is proposed that gives rise to a novel method, Outlier Exposure with Confidence Control (OECC), which achieves superior results in out-of-distribution detection with OE both on image and text classification tasks without requiring access to OOD samples.

TL;DR: This paper designs a mechanism in a way that only uses a minimal set of sufficient conditions in order to guarantee the existence of a solution and maximize its efficiency, and demonstrates that the proposed mechanism can approach the system optimum solution.

TL;DR: In this paper, a coordination mechanism for truck drivers that uses pricing-and-routing schemes that can help alleviate traffic congestion in a general transportation network is proposed, where the coordinator asks the truck drivers to declare their desired OD pair and pick their individual VOT from a set of N available options, and guarantees that the resulting pricing and routing scheme is Pareto-improving, i.e. every truck driver will be better-off compared to the user equilibrium.

TL;DR: A coordination mechanism for truck routing decisions which reduces the overall congestion cost in the traffic network, contributing to the improvement of traffic conditions for both passenger vehicles and truck drivers is proposed.

TL;DR: A novel pricing scheme to alleviate traffic congestion by controlling the freight routing decisions through a coordination mechanism and guaranteeing that every participant truck driver will be better-off compared to the User Equilibrium by providing them individual incentives to truthfully declare their VOT while leading to a budget balanced on average mechanism.