Regret bounds for sleeping experts and bandits

By Robert D. Kleinberg, Alexandru Niculescu-Mizil, Yogeshwer Sharma. 2010

259 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

Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics (2016, background): “Self-aware learning (classiﬁcation with an abstain option) had been proposed in e.g. [12, 15].”
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (2012, neutral): “We refer the interested reader to [113, 112, 121, 152] for the details of this model as well as the theoretical guarantees that can be obtained.”
Random Forest for the Contextual Bandit Problem (2015, background): “These variations include for instance the death and birth of arms in Chakrabarti et al (2008), the availability of actions in Kleinberg et al (2008) or a drawing without replacement in F´eraud and Urvoy (2012, 2013).”
Contextual Bandits with Similarity Information (2009, methodology): “In the absence of such information the algorithms essentially reduces to the “highest awake index” algorithm in [23].”
Improved Algorithms for Linear Stochastic Bandits (2011, background): “Another variant dubbed “sleeping bandits”, studied by Kleinberg et al. (2008), is the case when the set of available actions changes from time step to time step, but it is always a subset of the standard orthonormal basis of R .”
Human Interaction with Recommendation Systems (2017, background): “If there is always a large fraction of items with a positive signal, the model can be seen as a sleeping bandits problem Kleinberg et al. [2008], where items without such signal are considered sleeping, and the choice is based on the remaining options.”
Human Interaction with Recommendation Systems: On Bias and Exploration (2017, background): “If there is always a large fraction of items with a positive signal, the model can be seen as a sleeping bandits problem Kleinberg et al. [2008], where items without such signal are considered sleeping, and the choice is based on the remaining options.”
Competing with Automata-based Expert Sequences (2018, methodology): “This framework is distinct from the permutation-based setting adopted in [Kleinberg et al., 2010, Kanade et al., 2009, Kanade and Steinke, 2014].”
Regret Bounds for Gaussian Process Bandit Problems (2010, unknown): “…of the classical framework (Robbins, 1952; Gittins and Jones, 1979; Berry and Fristedt, 1985; Auer et al., 2002; Cesa-Bianchi and Lugosi, 2006) have been developed (among many others, Abernethy et al., 2008; Slivkins and Upfal, 2008; Wang et al., 2008; Bubeck et al., 2008; Kleinberg et al., 2008b).”
The K-armed Dueling Bandits Problem (2012, background): “The proof is motivated by Lemma 5 of [19].”
A Neural Networks Committee for the Contextual Bandit Problem (2014, background): “Variants of the initial problem were introduced due to practical constraints (appearance of a new advertisment after the beginning of learning [7,8], fixed number of contractual page views [9,10]).”