2.9k citations
- John Langford2 profiles7 · h 73
- Alex Smola2 profiles3 · h 128
- David M. Pennock2 profiles3 · h 48
- Arpita Ghosh2 profiles2 · h 33
- Jake M. Hofman2 profiles2 · h 31
- Lihong Li2 profiles2 · h 63
- Tong Zhang2 profiles2 · h 47
- Yiling Chen2 profiles2 · h 44
- A. Beygelzimer1 · h 27
- Alexander J. Smola1 · h 2
- Alex Strehl1
- Alina Beygelzimer1
- Stanford UniversityUS4 papers
- Cornell UniversityUS3 papers
- IBM (United States)US3 papers
- Research!America (United States)US3 papers
- University of PennsylvaniaUS3 papers
- Meta (United States)US2 papers
- Northwestern UniversityUS2 papers
- University of AlbertaCA2 papers
- University of TorontoCA2 papers
- Australian National UniversityAU1 paper
- Chinese Academy of SciencesCN1 paper
- City University of Hong KongHK1 paper
11 papers · 1 filter
Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits
Miroslav Dudik, Dumitru Erhan, John Langford +1
We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and…
Active Model Selection
Omid Madani, Daniel J. Lizotte, Russell Greiner
Classical learning assumes the learner is given a labeled data sample, from which it learns a model. The field of Active Learning deals with the situation where the learner begins…
Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations
Nando de Freitas, Alex Smola, Masrour Zoghi
This paper analyzes the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorith…
Constrained Automated Mechanism Design for Infinite Games of Incomplete Information
Yevgeniy Vorobeychik, Daniel Reeves, Michael P. Wellman
We present a functional framework for automated mechanism design based on a two-stage game model of strategic interaction between the designer and the mechanism participants, and a…
Collaborative Filtering and the Missing at Random Assumption
Benjamin Marlin, Richard S. Zemel, Sam Roweis +1
Rating prediction is an important application, and a popular research topic in collaborative filtering. However, both the validity of learning algorithms, and the validity of stand…
A Utility Framework for Bounded-Loss Market Makers
Yiling Chen, David M Pennock
We introduce a class of utility-based market makers that always accept orders at their risk-neutral prices. We derive necessary and sufficient conditions for such market makers to…