Yi-Te Hong

Artificial Intelligence · 2017

A researcher in the Science corpus: 1 paper; trusts 6 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 5 citations into it
• Management Science and Operations Research — 5 citations into it

Whom Yi-Te Hong trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Aurélien Garivier
2. Yonatan Gur
3. Jean-Yves Audibert
4. Peter Auer
5. Nicolò Cesa-Bianchi

Who trusts Yi-Te Hong overall

1. Wendi Wu

Papers from Yi-Te Hong's perspective

Ordered by how strongly the researchers Yi-Te Hong trusts endorse each paper. Same corpus, a different order for every researcher.

1. The Nonstochastic Multiarmed Bandit Problem
2. On Upper-Confidence Bound Policies for Switching Bandit Problems (International Conference on Algorithmic Learning Theory)
3. Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
4. Empirical Bernstein Bounds and Sample-Variance Penalization
5. Non-Stationary Stochastic Optimization
6. Stochastic Multi-Armed-Bandit Problem with Non-stationary Rewards (Neural Information Processing Systems)
7. Some aspects of the sequential design of experiments
8. Asymptotically efficient adaptive allocation rules
9. Multi-armed Bandit Allocation Indices
10. Asymptotically Efficient Adaptive Allocation Rules

Their papers

• Tracking the Best Expert in Non-stationary Stochastic Environments (2017) — 65 citations