activity
20172026
most citedMultinomial Logit Bandit with Low Switching Cost

4 citations · 12 across the 25 of their papers we have counts for

collaborators
Showing 2019Show all

7 papers · 1 filter

cs.LG2019

Stochastic Linear Optimization with Adversarial Corruption

Yingkai Li, Edmund Y. Lou, Liren Shan

We extend the model of stochastic bandits with adversarial corruption (Lykouriset al., 2018) to the stochastic linear optimization problem (Dani et al., 2008). Our algorithm is agn…

cs.GT2019

Approximately Maximizing the Broker's Profit in a Two-sided Market

Jing Chen, Bo Li, Yingkai Li

We study how to maximize the broker's (expected) profit in a two-sided market, where she buys items from a set of sellers and resells them to a set of buyers. Each seller has a sin…

cs.GT2019

Optimal Auctions vs. Anonymous Pricing: Beyond Linear Utility

Yiding Feng, Jason D. Hartline, Yingkai Li

The revenue optimal mechanism for selling a single item to agents with independent but non-identically distributed values is complex for agents with linear utility (Myerson,1981) a…

stat.ML2019

Tight Regret Bounds for Infinite-armed Linear Contextual Bandits

Yingkai Li, Yining Wang, Xi Chen +1

Linear contextual bandit is an important class of sequential decision making problems with a wide range of applications to recommender systems, online advertising, healthcare, and…

stat.ML2019

Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits

Yingkai Li, Yining Wang, Yuan Zhou

We study the linear contextual bandit problem with finite action sets. When the problem dimension is , the time horizon is , and there are candidate actions…

cs.GT2019

Revenue Maximization with Imprecise Distribution

Yingkai Li, Pinyan Lu, Haoran Ye

We study the revenue maximization problem with an imprecisely estimated distribution of a single buyer or several independent and identically distributed buyers given that this est…