Research

 

Effective Sampling and Learning for Mallows Models with Pairwise-Preference Data

Tyler Lu and Craig Boutilier

To appear in Journal of Machine Learning Research, 2014.

(Much longer version of our ICML 2011 paper, major additions include new experiments on preference prediction, further details of prior experiments, updated discussion of related work, proofs, and practical tricks to make algorithms work well)


Dynamic Segmentation for Large-Scale Marketing Optimization

Tyler Lu and Craig Boutilier

ICML Workshop on Customer Value Optimization in Digital Marketing 2014.


On the Value of Using Group Discounts under Price Competition

Reshef Meir, Tyler Lu, Moshe Tennenholtz and Craig Boutilier

To appear in Artificial Intelligence Journal, 2014.


Multi-winner Social Choice with Incomplete Preferences

Tyler Lu and Craig Boutilier

IJCAI 2013 (oral).


On the Value of Using Group Discounts under Price Competition

Reshef Meir, Tyler Lu, Moshe Tennenholtz and Craig Boutilier

AAAI 2013.

Honorable Mention Paper Award.


Bayesian Vote Manipulation: Optimal Strategies and Impact on Welfare [Appendix: Proofs to Theorems 1 and 2]

Tyler Lu, Pingzhong Tang, Ariel Procaccia and Craig Boutilier.

UAI 2012.


Matching Models for Preference-sensitive Group Purchasing [Appendix]

Tyler Lu and Craig Boutilier.

ACM EC 2012.


Optimal Social Choice Functions: A Utilitarian View [Full paper]

Craig Boutilier, Ioannis Caragiannis, Simi Haber, Tyler Lu, Ariel D. Procaccia, and Or Sheffet.

ACM EC 2012.


Vote Elicitation with Probabilistic Preference Models: Empirical Estimation and Cost Tradeoffs

Tyler Lu and Craig Boutilier.

International Conference on Algorithmic Decision Theory 2011.


Probabilistic and Utility-theoretic Models in Social Choice: Challenges for Learning, Optimization, Elicitation, and Manipulation

Craig Boutilier and Tyler Lu.

IJCAI Workshop on Social Choice and Artificial Intelligence 2011.


Learning Mallows Models with Pairwise Preferences [Supplementary Material]

Tyler Lu and Craig Boutilier.

ICML 2011.


Robust Approximation and Incremental Elicitation in Voting Protocols

Tyler Lu and Craig Boutilier.

IJCAI 2011 (oral).

Download datasets: Dublin North 2002 and Dublin West 2002


Budgeted Social Choice: From Consensus to Personalized Decision Making

Tyler Lu and Craig Boutilier.

IJCAI 2011 (oral).

A preliminary version Budgeted Social Choice: A Framework for Multiple Recommendations in Consensus Decision Making. appeared in COMSOC 2011.


The Unavailable Candidate Model: A Decision-Theoretic View of Social Choice

Tyler Lu and Craig Boutilier.

ACM EC 2010. Also presented at NIPS 2009 Workshop on Advances in Ranking.

[slides]

This probabilistic model of unavailable candidates was also independently developed by economists Katie Baldiga and Jerry R. Green in Choice-based Measures of Conflict in Preferences.


Impossibility Theorems for Domain Adaptation

Shai Ben-David, Tyler Lu, Teresa Luu and David Pal.

AISTATS 2010.


Contextual Multi-Armed Bandits

Tyler Lu, David Pal and Martin Pal.

AISTATS 2010.


Learning Low-Density Separators

Shai Ben-David, Tyler Lu, David Pal and Miroslava Sotakova.

AISTATS 2009.


Does Unlabeled Data Provably Help? Worst-case Analysis of the Sample Complexity of Semi-Supervised Learning

Shai Ben-David, Tyler Lu and David Pal.

COLT 2008.


Faster Set Intersection Algorithms for Text Searching

Jeremy Barbay, Alejandro Lopez-Ortiz, Tyler Lu and Alejandro Salinger.

ACM Journal of Experimental Algorithmics, Vol. 14, Nov. 2009.

Invited from our paper Faster Adaptive Set Intersections for Text Searching that appeared in Workshop on Experimental Algorithms 2006.


My Master's Thesis:

Fundamental Limitations of Semi-Supervised Learning. May 2009.