相关论文: Discrete Lanchester attrition models: the case of …

Recent work has considered natural variations of the multi-armed bandit problem, where the reward distribution of each arm is a special function of the time passed since its last pulling. In this direction, a simple (yet widely applicable)…

In this work we present an a posteriori error indicator for approximation schemes of Runge-Kutta-discontinuous-Galerkin type arising in applications of compressible fluid flows. The purpose of this indicator is not only for mesh adaptivity,…

We introduce a minimal model of multilevel selection on structured populations, considering the interplay between game theory and population dynamics. Through a bottleneck process, finite groups are formed with cooperators and defectors…

The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques…

Adversarial examples are a challenging open problem for deep neural networks. We propose in this paper to add a penalization term that forces the decision function to be at in some regions of the input space, such that it becomes, at least…

We consider the two-sided stable matching setting in which there may be uncertainty about the agents' preferences due to limited information or communication. We consider three models of uncertainty: (1) lottery model --- in which for each…

A growing number of machine learning architectures, such as Generative Adversarial Networks, rely on the design of games which implement a desired functionality via a Nash equilibrium. In practice these games have an implicit complexity…

As a generalization of the 3-strategy Rock-Scissors-Paper game dynamics in space, cyclical interaction models of six mutating species are studied on a square lattice, in which each species is supposed to have two dominant, two subordinated…

This paper studies a war of attrition game in the setting of public good provision that combines three elements: (i) multiple players, (ii) incomplete information, and (iii) ex-ante asymmetry. In the unique equilibrium, asymmetry leads to a…

Cooperative behavior, where one individual incurs a cost to help another, is a wide spread phenomenon. Here we study direct reciprocity in the context of the alternating Prisoner's Dilemma. We consider all strategies that can be implemented…

This paper presents a study of the two-predators-two-preys discrete-time Lotka-Volterra model with self- inhibition terms for preys with direct applications to ecological problems. Parameters in the model are modified so that each of them…

In machine learning, the notion of multi-armed bandits refers to a class of online learning problems, in which an agent is supposed to simultaneously explore and exploit a given set of choice alternatives in the course of a sequential…

Both transduction and rejection have emerged as important techniques for defending against adversarial perturbations. A recent work by Goldwasser et al. showed that rejection combined with transduction can give provable guarantees (for…

Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some…

In this paper we study a rational inattention model in environments where the decision maker faces uncertainty about the true prior distribution over states. The decision maker seeks to select a stochastic choice rule over a finite set of…

We study three different lattice models in which two species of diffusing particles are driven in opposite directions by an electric field. We focus on dynamical phase transitions that involve phase separation into domains that may be…

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient…

The prisoner's dilemma describes a conflict between a pair of players, in which defection is a dominant strategy whereas cooperation is collectively optimal. The iterated version of the dilemma has been extensively studied to understand the…

Deception is virtually ubiquitous in warfare, and should be a central consideration for military operations research. However, studies of agent behaviour in simulated operations have typically neglected to include explicit models of…

Deep Reinforcement Learning (DRL) policies have been shown to be vulnerable to small adversarial noise in observations. Such adversarial noise can have disastrous consequences in safety-critical environments. For instance, a self-driving…