758 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Microsoft (United States)US53 papers
- Cornell UniversityUS15 papers
- Carnegie Mellon UniversityUS9 papers
- University of Massachusetts AmherstUS8 papers
- Princeton UniversityUS7 papers
- Columbia UniversityUS6 papers
- Microsoft Research (United Kingdom)GB6 papers
- University of PennsylvaniaUS6 papers
- University of Maryland, College ParkUS5 papers
- University of MichiganUS5 papers
- Harvard UniversityUS4 papers
- Stanford UniversityUS4 papers
5 papers · 2 filters
Off-policy evaluation for slate recommendation
Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal +4
This paper studies the evaluation of policies that recommend an ordered set of items (e.g., a ranking) based on some context---a common scenario in web search, ads, and recommendat…
Efficient Algorithms for Adversarial Contextual Learning
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
We provide the first oracle efficient sublinear regret algorithms for adversarial versions of the contextual bandit problem. In this problem, the learner repeatedly makes an action…
Search Improves Label for Active Learning
Alina Beygelzimer, Daniel Hsu, John Langford +1
We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human search…
PAC Reinforcement Learning with Rich Observations
Akshay Krishnamurthy, Alekh Agarwal, John Langford
We propose and study a new model for reinforcement learning with rich observations, generalizing contextual bandits to sequential decision making. These models require an agent to…
Efficient Second Order Online Learning by Sketching
Haipeng Luo, Alekh Agarwal, Nicolo Cesa-Bianchi +1
We propose Sketched Online Newton (SON), an online second order learning algorithm that enjoys substantially improved regret guarantees for ill-conditioned data. SON is an enhanced…