Related papers: Intelligent and Reconfigurable Architecture for KL…

We study an extension of the classic stochastic multi-armed bandit problem which involves multiple plays and Markovian rewards in the rested bandits setting. In order to tackle this problem we consider an adaptive allocation rule which at…

Large language models (LLMs) have been adopted to solve sequential decision-making tasks such as multi-armed bandits (MAB), in which an LLM is directly instructed to select the arms to pull in every iteration. However, this paradigm of…

We propose a novel computational framework that models human social decision-making under uncertainty as an integrated Multi-Armed Bandit (MAB) and Markov Decision Process (MDP) optimization problem, in which agents adaptively balance the…

The forward Kullback-Leibler (KL) divergence is a ubiquitous objective for fitting a parameterized distribution to samples due to its tractability and equivalence to maximum likelihood estimation (MLE). Its inherent asymmetry, however, may…

In modern ML Ops environments, model deployment is a critical process that traditionally relies on static heuristics such as validation error comparisons and A/B testing. However, these methods require human intervention to adapt to…

Recognizing implicit visual and textual patterns is essential in many real-world applications of modern AI. However, tackling long-tail pattern recognition tasks remains challenging for current pre-trained foundation models such as LLMs and…

We consider a novel multi-armed bandit framework where the rewards obtained by pulling the arms are functions of a common latent random variable. The correlation between arms due to the common random source can be used to design a…

RAN slicing technology is a key aspect of the Open RAN paradigm, allowing simultaneous and independent provision of various services such as ultra-reliable low-latency communications (URLLC), enhanced mobile broadband (eMBB), and massive…

We study a variant of the classical stochastic $K$-armed bandit where observing the outcome of each arm is expensive, but cheap approximations to this outcome are available. For example, in online advertising the performance of an ad can be…

Neural Network (Deep Learning) is a modern model in Artificial Intelligence and it has been exploited in Survival Analysis. Although several improvements have been shown by previous works, training an excellent deep learning model requires…

Adaptive beam switching is essential for mission-critical military and commercial 6G networks but faces major challenges from high carrier frequencies, user mobility, and frequent blockages. While existing machine learning (ML) solutions…

This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free index policy for stochastic bandit problems. We prove two distinct results: first, for arbitrary bounded rewards, the KL-UCB algorithm satisfies a…

We consider the classic online learning and stochastic multi-armed bandit (MAB) problems, when at each step, the online policy can probe and find out which of a small number ($k$) of choices has better reward (or loss) before making its…

Residential loads have great potential to enhance the efficiency and reliability of electricity systems via demand response (DR) programs. One major challenge in residential DR is to handle the unknown and uncertain customer behaviors.…

We consider the problem of identifying the best arm in stochastic Multi-Armed Bandits (MABs) using a fixed sampling budget. Characterizing the minimal instance-specific error probability for this problem constitutes one of the important…

We consider the query recommendation problem in closed loop interactive learning settings like online information gathering and exploratory analytics. The problem can be naturally modelled using the Multi-Armed Bandits (MAB) framework with…

Stochastic multi-armed bandits (MABs) provide a fundamental reinforcement learning model to study sequential decision making in uncertain environments. The upper confidence bounds (UCB) algorithm gave birth to the renaissance of bandit…

One of the key drivers of complexity in the classical (stochastic) multi-armed bandit (MAB) problem is the difference between mean rewards in the top two arms, also known as the instance gap. The celebrated Upper Confidence Bound (UCB)…

Modern optimization problems in scientific and engineering domains often rely on expensive black-box evaluations, such as those arising in physical simulations or deep learning pipelines, where gradient information is unavailable or…

This work addresses resource allocation challenges in multi-cell wireless systems catering to enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low Latency Communications (URLLC) users. We present a distributed learning framework tailored…