20 accepted papers
Multi-Objective Reinforcement Learning (MORL) extends standard RL by optimizing policies with respect to multiple, often conflicting, objectives. While max-min MORL has emerged as an effective approach for promoting fairness, its applicability remains limited, particularly when constraints must be i…
In this paper, we propose a provably convergent and practical framework for multi-objective reinforcement learning with max-min criterion. From a game-theoretic perspective, we reformulate max-min multi-objective reinforcement learning as a two-player zero-sum regularized continuous game and introdu…
In this paper, we study the problem of fair multi-agent multi-arm bandit learning when agents do not communicate with each other, except collision information, provided to agents accessing the same arm simultaneously. We provide an algorithm with regret O(N<sup xmlns:mml="http://www.w3.org/1998/Math…
Federated learning is a technique that allows multiple entities to collaboratively train models using their data without compromising data privacy. However, despite its advantages, federated learning can be susceptible to false data injection attacks. In these scenarios, a malicious entity with cont…
In this paper, we consider multi-objective reinforcement learning, which arises in many real-world problems with multiple optimization goals. We approach the problem with a max-min framework focusing on fairness among the multiple goals and develop a relevant theory and a practical model-free algori…
Generalized Nash games differ from strategic form games by allowing the strategy set available for each player to depend on the strategies selected by the other players. The strong dependence of the strategies of the players make these generalized games harder to analyze. While convex generalized ga…
The Corona virus disease 2019 (COVID-19) has significantly affected lives of people around the world. Today, isolation policy is mostly enforced by identifying infected individuals based on symptoms when these appear or by testing people and quarantining those who have been in close contact with inf…
Wireless cellular communication networks are bandwidth and interference limited. An important means to overcome these resource limitations is the use of multiple antennas. Base stations equipped with a very large (massive) number of antennas have been the focus of recent research. A bottleneck in su…
Packet scheduling in 5G networks can significantly affect the performance of beamforming techniques since the allocation of multiple users to the same time-frequency block causes interference between users. A combination of beamforming and scheduling can thus improve the performance of multi-user MI…
Consider N cooperative but non-communicating players where each plays one out of M arms for T turns. Players have different utilities for each arm, representable as an NxM matrix. These utilities are unknown to the players. In each turn players receive noisy observations of their utility for their s…
This paper studies the security aspect of gossip-based decentralized optimization algorithms for multi agent systems against data injection attacks. Our contributions are two-fold. First, we show that the popular distributed projected gradient method (by Nedić et al.) can be attacked by <i xmlns:mml…
We consider a multi-armed bandit game where N players compete for K arms for T turns. Each player has different expected rewards for the arms, and the instantaneous rewards are independent and identically distributed. Performance is measured using the expected sum of regrets, compared to the optimal…
Linear Least Squares is a very well known technique for parameter estimation, which is used even when sub-optimal, because of its very low computational requirements and the fact that exact knowledge of the noise statistics is not required. Surprisingly, bounding the probability of large errors with…
Celestial transient radio sources have attracted considerable scientific interest recently, but their investigation is hampered by the fact that they cannot be effectively detected by commonly used radio astronomy imaging techniques. One significant obstacle to observing radio transients is intermit…
In this paper we consider the problem of channel allocation for users who access a common channel using OFDMA. The spectrum is divided into subchannels and we assume that the bandwidth of each subchannel is smaller than the coherence bandwidth. This leads to correlations between the channel coeffici…
This paper considers an online optimization algorithm for actively learning trusts on social networks. We first introduce a DeGroot model for opinion dynamics under the influence of stubborn agents and demonstrate how an observer with estimates of the individuals opinions can actively learn the rela…
We study stochastic linear optimization problem with bandit feedback. The set of arms take values in an N-dimensional space and belongs to a bounded polyhedron described by finitely many linear inequalities. We present an algorithm that has O(Nlog1+ε(T)) expected regret for any ε > 0 in T rounds. Th…
The core component of a cognitive radio is its detector. When a device is equipped with multiple antennas, the detection method is usually based on an eigenvalue analysis. This paper explores the performance of the most common largest eigenvalue detector, for the case of a narrowband temporally whit…
Linear image deconvolution for radio-astronomy is an ill-posed problem. For this reason, a-priori knowledge is crucial for improving the performance of the deconvolution. In this paper we show that combining non-negativity constraints with an upper bound on the magnitude of each pixel in the image c…
We propose a new sequential deconvolution algorithm, that is applicable to imaging using moving and synthetic aperture arrays. The new method results in a higher resolution and a more accurate estimation than commonly used methods when strong interfering sources are present inside and outside the fi…