Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Hanna, Osama A."'
We consider a novel multi-arm bandit (MAB) setup, where a learner needs to communicate the actions to distributed agents over erasure channels, while the rewards for the actions are directly available to the learner through external sensors. In our m
Externí odkaz:
http://arxiv.org/abs/2406.18072
Multi-Armed Bandit (MAB) systems are witnessing an upswing in applications within multi-agent distributed environments, leading to the advancement of collaborative MAB algorithms. In such settings, communication between agents executing actions and t
Externí odkaz:
http://arxiv.org/abs/2312.14259
The exact common information between a set of random variables $X_1,...,X_n$ is defined as the minimum entropy of a shared random variable that allows for the exact distributive simulation of $X_1,...,X_n$. It has been established that, in certain in
Externí odkaz:
http://arxiv.org/abs/2305.06469
In this paper, we address the stochastic contextual linear bandit problem, where a decision maker is provided a context (a random set of actions drawn from a distribution). The expected reward of each action is specified by the inner product of the a
Externí odkaz:
http://arxiv.org/abs/2211.05632
In this paper, we propose differentially private algorithms for the problem of stochastic linear bandits in the central, local and shuffled models. In the central model, we achieve almost the same regret as the optimal non-private algorithms, which m
Externí odkaz:
http://arxiv.org/abs/2207.03445
Contextual linear bandits is a rich and theoretically important model that has many practical applications. Recently, this setup gained a lot of interest in applications over wireless where communication constraints can be a performance bottleneck, e
Externí odkaz:
http://arxiv.org/abs/2206.04180
The multi-armed bandit (MAB) problem is an active learning framework that aims to select the best among a set of actions by sequentially observing rewards. Recently, it has become popular for a number of applications over wireless networks, where com
Externí odkaz:
http://arxiv.org/abs/2111.06067
We consider machine learning applications that train a model by leveraging data distributed over a trusted network, where communication constraints can create a performance bottleneck. A number of recent approaches propose to overcome this bottleneck
Externí odkaz:
http://arxiv.org/abs/2012.07913
We consider the problem of distributed feature quantization, where the goal is to enable a pretrained classifier at a central node to carry out its classification on features that are gathered from distributed nodes through communication constrained
Externí odkaz:
http://arxiv.org/abs/1911.00216
Traditional random access schemes are designed based on the aggregate process of user activation, which is created on the basis of independent activations of the users. However, in Machine-Type Communications (MTC), some users are likely to exhibit a
Externí odkaz:
http://arxiv.org/abs/1803.03610