Non-Stochastic Bandit Slate Problems

By Satyen Kale, Lev Reyzin, Robert E. Schapire. 2010

95 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Off-policy evaluation for slate recommendation (2016, background): “Yet another paradigm, called semi-bandits , assumes that the slate-level metric is a sum of observed action-level metrics [12, 14].”
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (2012, neutral): “The semi-bandit feedback was studied in the series of papers [19, 91, 111, 163].”
Introduction to Multi-Armed Bandits (2019, background): “Such improvements are possible when actions correspond to “slates” of search results (Kale et al., 2010), and for IID rewards (e.”
Minimax Policies for Combinatorial Prediction Games (2011, background): “…Dani et al. (2008), Abernethy et al. (2008), Cesa-Bianchi and Lugosi (2009), Helmbold and Warmuth (2009), Koolen et al. (2010), Uchiya et al. (2010) and Kale et al. (2010) We consider three variants of the problem, distinguished by the type of information that becomes available to the forecaster…”
Efficient Contextual Semi-Bandit Learning (2015, background): “When no contextual information is present, this setting is referred to as semi-bandits [Audibert et al., 2014] or slate bandits [Kale et al., 2010] in the literature.”
Explore-exploit in top-N recommender systems via Gaussian processes (2014, background): “In particular, the best subset selection under ’bandit-feedback’ setting has been studied [11].”
Multi-Task Learning for Contextual Bandits (2017, methodology): “Contextual bandits have been employed to model various applications like news article recommendation [7], computational advertisement [9], website optimization [20] and clinical trials [19].”
Recommender Systems (2016, unknown): “To handle this variation, the slate problem is proposed [290] for multi-armed bandits.”
Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback (2025, unknown): “However, for the non-contextual setting, we also include other state-of-the-art baselines such as the MPS algorithm (Algorithm 3, Dimakopoulou et al. [2019]) and the Ordered Slate Bandit algorithm (Figure 3, Kale et al. [2010]).”