Collaborative filtering bandits

S Li, A Karatzoglou, C Gentile - … of the 39th International ACM SIGIR …, 2016 - dl.acm.org
Classical collaborative filtering, and content-based filtering methods try to learn a static
recommendation model given training data. These approaches are far from ideal in highly …

An optimal algorithm for the thresholding bandit problem

A Locatelli, M Gutzeit… - … Conference on Machine …, 2016 - proceedings.mlr.press
We study a specific combinatorial pure exploration stochastic bandit problem where the
learner aims at finding the set of arms whose means are above a given threshold, up to a …

Tight (lower) bounds for the fixed budget best arm identification bandit problem

A Carpentier, A Locatelli - Conference on Learning Theory, 2016 - proceedings.mlr.press
We consider the problem of\textitbest arm identification with a\textitfixed budget T, in the K-
armed stochastic bandit setting, with arms distribution defined on [0, 1]. We prove that any …

Can AI help in ideation? A theory-based model for idea screening in crowdsourcing contests

JJ Bell, C Pescher, GJ Tellis, J Füller - Marketing Science, 2024 - pubsonline.informs.org
Crowdsourcing generates up to thousands of ideas per contest. The selection of best ideas
is costly because of the limited number, objectivity, and attention of experts. Using a data set …

Via: Improving internet telephony call quality using predictive relay selection

J Jiang, R Das, G Ananthanarayanan… - Proceedings of the …, 2016 - dl.acm.org
Interactive real-time streaming applications such as audio-video conferencing, online
gaming and app streaming, place stringent requirements on the network in terms of delay …

Nearly instance optimal sample complexity bounds for top-k arm selection

L Chen, J Li, M Qiao - Artificial Intelligence and Statistics, 2017 - proceedings.mlr.press
Abstract In the Best-k-Arm problem, we are given n stochastic bandit arms, each associated
with an unknown reward distribution. We are required to identify the k arms with the largest …

Multinomial logit contextual bandits: Provable optimality and practicality

M Oh, G Iyengar - Proceedings of the AAAI conference on artificial …, 2021 - ojs.aaai.org
We consider a sequential assortment selection problem where the user choice is given by a
multinomial logit (MNL) choice model whose parameters are unknown. In each period, the …

Towards instance optimal bounds for best arm identification

L Chen, J Li, M Qiao - Conference on Learning Theory, 2017 - proceedings.mlr.press
In the classical best arm identification (Best-$1 $-Arm) problem, we are given $ n $
stochastic bandit arms, each associated with a reward distribution with an unknown mean …

Single-pass streaming lower bounds for multi-armed bandits exploration with instance-sensitive sample complexity

S Assadi, C Wang - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Motivated by applications to process massive datasets, we study streaming algorithms for
pure exploration in Stochastic Multi-Armed Bandits (MABs). This problem was first …

On the optimal sample complexity for best arm identification

L Chen, J Li - arXiv preprint arXiv:1511.03774, 2015 - arxiv.org
We study the best arm identification (BEST-1-ARM) problem, which is defined as follows. We
are given $ n $ stochastic bandit arms. The $ i $ th arm has a reward distribution $ D_i $ with …