Bandit multi-linear DR-submodular maximization and its applications on adversarial submodular bandits

Z Wan, J Zhang, W Chen, X Sun… - … on Machine Learning, 2023 - proceedings.mlr.press
We investigate the online bandit learning of the monotone multi-linear DR-submodular
functions, designing the algorithm $\mathtt {BanditMLSM} $ that attains $ O (T^{2/3}\log T) …

An -regret analysis of Adversarial Bilateral Trade

Y Azar, A Fiat, F Fusco - Advances in Neural Information …, 2022 - proceedings.neurips.cc
We study sequential bilateral trade where sellers and buyers valuations are completely
arbitrary ({\sl ie}, determined by an adversary). Sellers and buyers are strategic agents with …

Fair assortment planning

Q Chen, N Golrezaei, F Susan - arXiv preprint arXiv:2208.07341, 2022 - arxiv.org
Many online platforms, ranging from online retail stores to social media platforms, employ
algorithms to optimize their offered assortment of items (eg, products and contents). These …

A framework for adapting offline algorithms to solve combinatorial multi-armed bandit problems with bandit feedback

G Nie, YY Nadew, Y Zhu… - … on Machine Learning, 2023 - proceedings.mlr.press
We investigate the problem of stochastic, combinatorial multi-armed bandits where the
learner only has access to bandit feedback and the reward function can be non-linear. We …

Learning product rankings robust to fake users

N Golrezaei, V Manshadi, J Schneider… - Proceedings of the 22nd …, 2021 - dl.acm.org
In many online platforms, customers' decisions are substantially influenced by product
rankings as most customers only examine a few top-ranked products. Concurrently, such …

A unified approach for maximizing continuous DR-submodular functions

M Pedramfar, C Quinn… - Advances in Neural …, 2024 - proceedings.neurips.cc
This paper presents a unified approach for maximizing continuous DR-submodular functions
that encompasses a range of settings and oracle access types. Our approach includes a …

Contextual bandits with cross-learning

S Balseiro, N Golrezaei, M Mahdian… - Advances in …, 2019 - proceedings.neurips.cc
In the classical contextual bandits problem, in each round $ t $, a learner observes some
context $ c $, chooses some action $ a $ to perform, and receives some reward $ r_ {a, t}(c) …

An explore-then-commit algorithm for submodular maximization under full-bandit feedback

G Nie, M Agarwal, AK Umrawal… - Uncertainty in …, 2022 - proceedings.mlr.press
We investigate the problem of combinatorial multi-armed bandits with stochastic submodular
(in expectation) rewards and full-bandit feedback, where no extra information other than the …

Learning and collusion in multi-unit auctions

S Brânzei, M Derakhshan… - Advances in Neural …, 2023 - proceedings.neurips.cc
In a carbon auction, licenses for CO2 emissions are allocated among multiple interested
players. Inspired by this setting, we consider repeated multi-unit auctions with uniform …

Combinatorial stochastic-greedy bandit

F Fourati, CJ Quinn, MS Alouini… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
We propose a novel combinatorial stochastic-greedy bandit (SGB) algorithm for
combinatorial multi-armed bandit problems when no extra information other than the joint …