Combinatorial Bandits

By Nicolò Cesa-Bianchi, Gábor Lugosi. 2012

505 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Management Science and Operations Research

How researchers see this paper

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

In Artificial Intelligence

In Computer Networks and Communications

In Management Science and Operations Research

Citations in the corpus

Off-policy evaluation for slate recommendation (2016, methodology): “In particular, our estimator closely follows the recipe of Cesa-Bianchi and Lugosi [7], albeit with some differences to account for the off-policy and contextual nature of our setup.”
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (2012, neutral): “Now we use the chain rule for Kullback-Leibler divergence —see for example [Cesa-Bianchi and Lugosi, 2006, Section A.2]— iteratively to introduce 36 Adversarial bandits: fundamental results the laws Pti of Y t = (Y1, . . . , Yt).”
Fundamental Limits of Online and Distributed Algorithms for Statistical Learning and Estimation (2013, background): “At this stage, the deﬁnition above may appear quite abstract, so let us consider a few speciﬁc examples: • b -memory online protocols: Consider any algorithm which goes over examples one-by-one, and incrementally updates a state vector W t of bounded size b .”
Bandit Theory meets Compressed Sensing for high dimensional Stochastic Linear Bandit (2012, methodology): “One idea would be to use techniques developed for adversarial bandits (see (Abernethy et al., 2008; Bartlett et al., 2008; Cesa-Bianchi and Lugosi, 2009; Koolen et al., 2010; Audibert et al., 2011), but also (Flaxman et al.”
A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits (2015, background): “As mentionned earlier, the dueling bandits problem is a special instance of a partial monitoring game (Piccolboni and Schindelhauer, 2001; Cesa-Bianchi and Lugosi, 2009; Bartók et al., 2014).”
Compiling Combinatorial Prediction Games (2018, methodology): “(2018) have paved the way using OBDDs for an efficient implementation of the COMBBAND algorithm (Cesa-Bianchi & Lugosi, 2012), Extending their approach to dDNNF, which is more succinct than OBDD, is a promising direction of future research.”
Structural Causal Bandits: Where to Intervene? (2018, background): “, 2008], combinatorial [Cesa-Bianchi and Lugosi, 2012], unimodal [Combes and Proutiere, 2014], and Lipschitz [Magureanu et al.”
Bandit Algorithms (2020, background): “A worthy mention goes to the article by Chang and Pollard [1997], which uses disintegration to formalise the “private calculations” that probabalists so frequently make before writing everything carefully using Nikodym derivatives and regular versions. Theorem 34.2 is well known. For a simple proof ”
Towards Minimax Policies for Online Linear Optimization with Bandit Feedback (2012, background): “Dani et al.[2008] chose this distribution to be uniform over a barycentric spanner for the action set, while in [Cesa-Bianchi and Lugosi, 2011] the distribution was uniform over all actions.”
Online Learning: A Comprehensive Survey (2018, methodology): “(Combes et al., 2015) provided a useful survey for closely related works (Bubeck et al., 2012; Cesa-Bianchi and Lugosi, 2012) and gave a novel algorithm with promising bounds.”
A Survey of Preference-Based Online Learning with Bandit Algorithms (2014, background): “Our survey is focused on the stochastic MAB setup, in which feedback is generated according to an underlying (unknown but stationary) probabilistic process; we do not cover the case of an adversarial data-generating processes, although this setting has recently received a lot of attention, too [1, 1”
Efficient Tracking of Large Classes of Experts (2011, background): “We refer to [1], [5], [7], [8], [20], [27], [31], [32] for an incomplete but representative list of papers.”
Towards scaling up Markov chain Monte Carlo: an adaptive subsampling approach (2014, unknown): “For instance, if the likelihood is Gaussian, then C θ,θ is proportional to max n i=1 |x i |, so that if the data actually were Towards scaling up MCMC: an adaptive subsampling approach sampled from a Gaussian, C θ,θ would grow in log(n) (Cesa-Bianchi & Lugosi, 2009, Lemma A.12).”