Search Results for author:
Found 10 papers, 0 papers with code
Fully Dynamic Online Selection through Online Contention Resolution Schemes
A successful approach to online selection problems in the adversarial setting is given by the notion of Online Contention Resolution Scheme (OCRS), that uses a priori information to formulate a linear relaxation of the underlying optimization problem, whose optimal fractional solution is rounded online for any adversarial order of the input sequence.
Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms
We describe the current content moderation strategy employed by Meta to remove policy-violating content from its platforms.
Top $K$ Ranking for Multi-Armed Bandit with Noisy Evaluations
We consider a multi-armed bandit setting where, at the beginning of each round, the learner receives noisy independent, and possibly biased, \emph{evaluations} of the true reward of each arm and it selects $K$ arms with the objective of accumulating as much reward as possible over $T$ rounds.
QUEST: Queue Simulation for Content Moderation at Scale
Moderating content in social media platforms is a formidable challenge due to the unprecedented scale of such systems, which typically handle billions of posts per day.
Stochastic Bandits for Multi-platform Budget Optimization in Online Advertising
We modify the algorithm proposed in Badanidiyuru \emph{et al.,} to extend it to the case of multiple platforms to obtain an algorithm for both the discrete and continuous bid-spaces.
A Tractable Online Learning Algorithm for the Multinomial Logit Contextual Bandit
In this paper, we propose an optimistic algorithm and show that the regret is bounded by $O(\sqrt{dT} + \kappa)$, significantly improving the performance over existing methods.
Multi-armed Bandits with Cost Subsidy
We then establish a fundamental lower bound on the performance of any online learning algorithm for this problem, highlighting the hardness of our problem in comparison to the classical MAB problem.
Thompson Sampling for Contextual Bandit Problems with Auxiliary Safety Constraints
Real-world applications frequently have constraints with respect to a currently deployed policy.
MNL-Bandit: A Dynamic Learning Approach to Assortment Selection
The retailer observes this choice and the objective is to dynamically learn the model parameters, while optimizing cumulative revenues over a selling horizon of length $T$.
Thompson Sampling for the MNL-Bandit
We consider a sequential subset selection problem under parameter uncertainty, where at each time step, the decision maker selects a subset of cardinality $K$ from $N$ possible items (arms), and observes a (bandit) feedback in the form of the index of one of the items in said subset, or none.
