T
Tyler Lu
Researcher at Google
Publications - 38
Citations - 2203
Tyler Lu is an academic researcher from Google. The author has contributed to research in topics: Social choice theory & Preference elicitation. The author has an hindex of 20, co-authored 37 publications receiving 1978 citations. Previous affiliations of Tyler Lu include University of Waterloo & University of Toronto.
Papers
More filters
Proceedings ArticleDOI
Budgeted social choice: from consensus to personalized decision making
Tyler Lu,Craig Boutilier +1 more
TL;DR: This work develops a general framework for social choice problems in which a limited number of alternatives can be recommended to an agent population, and generalizes certain multiwinner election schemes.
Proceedings Article
Contextual Multi-Armed Bandits
Tyler Lu,Dávid Pál,Martin Pál +2 more
TL;DR: A lower bound is proved for the regret of any algo- rithm where ~ ~ are packing dimensions of the query spaces and the ad space respectively and this gives an almost matching up- per and lower bound for finite spaces or convex bounded subsets of Eu- clidean spaces.
Proceedings Article
Learning Mallows Models with Pairwise Preferences
Tyler Lu,Craig Boutilier +1 more
TL;DR: A new algorithm is developed, the generalized repeated insertion model (GRIM), for sampling from arbitrary ranking distributions, that develops approximate samplers that are exact for many important special cases—and have provable bounds with pair-wise evidence.
Proceedings Article
Impossibility Theorems for Domain Adaptation
TL;DR: In this paper, the authors analyze the assumptions in an agnostic PAC-style learning model for a setting in which the learner can access a labeled training data sample and an unlabeled sample generated by the test data distribution and show that without either assumption (i or (ii), the combination of the remaining assumptions is not sufficient to guarantee successful learning.
Proceedings Article
Data Center Cooling using Model-predictive Control
TL;DR: Adopting a data-driven, model-based approach, it is demonstrated that an RL agent with little prior knowledge is able to effectively and safely regulate conditions on a server floor after just a few hours of exploration, while improving operational efficiency relative to existing PID controllers.