A Survey of Preference-Based Online Learning with Bandit Algorithms

By Róbert Istvan Busa-Fekete, Eyke Hüllermeier. 2014

50 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Management Science and Operations Research, Reinforcement Learning, Statistical Learning Theory

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

1. Aadirupa Saha
2. Maarten de Rijke
3. Akshay Krishnamurthy
4. Masrour Zoghi
5. Ilya Markov
6. Chang Li
7. Fabrice Clérot
8. Aditya Gopalan

In Computer Networks and Communications

1. Aadirupa Saha
2. Masrour Zoghi
3. Chang Li
4. Ilya Markov
5. Aditya Gopalan
6. Maarten de Rijke
7. Fabrice Clérot
8. Tanguy Urvoy

In Management Science and Operations Research

1. Aadirupa Saha
2. Maarten de Rijke
3. Ilya Markov
4. Akshay Krishnamurthy
5. Masrour Zoghi
6. Aditya Gopalan
7. Chang Li
8. Fabrice Clérot

In Reinforcement Learning

1. Aadirupa Saha
2. Aditya Gopalan
3. Masrour Zoghi
4. Maarten de Rijke
5. Suprovat Ghoshal
6. Akshay Krishnamurthy
7. Chang Li
8. Ilya Markov

In Statistical Learning Theory

1. Maarten de Rijke
2. Fabrice Clérot
3. Aditya Gopalan
4. Tanguy Urvoy
5. Aadirupa Saha
6. Masrour Zoghi
7. Akshay Krishnamurthy
8. Nan Jiang

Citations in the corpus

• Exploiting Correlation to Achieve Faster Learning Rates in Low-Rank Preference Bandits (2022, background): “k = 2) (Szörényi et al., 2015; Falahatgar et al., 2017; Busa-Fekete and Hüllermeier, 2014), while some works also extend the setting to general subsetwise queries (Ren et al.”
• MergeDTS (2018, background): “In the bandit literature [7, 8, 44], regret is a measure of the rate of convergence to the Condorcet winner in hindsight.”
• Active Ranking with Subset-wise Preferences (2018, methodology): “The result follows from the concentration of Geometric random variable as shown in Brown [2011]. Note that, Z denotes the number of trials needed to get nwins of item b, where the probability of success (i.”
• Copeland Dueling Bandits (2015, unknown): “PageRank) winners [41] do not.”
• Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability (2021, background): “Beyond fixed-benchmark regret, notions involving Borda [Busa-Fekete and Hüllermeier, 2014; Jamieson et al., 2015; Falahatgar et al., 2017] and Copeland scores [Zoghi et al.”
• A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits (2015, background): “See also (Busa-Fekete and Hüllermeier, 2014) for an extensive survey of this domain.”