Martin Zinkevich

47 papers A* 17A 3Misc 1Journal 11Unranked 15
YearRankTypeTitle / Venue / Authors
2020 — conf
TensorFlow Data Validation: Data Analysis and Validation in Continuous ML Pipelines.
SIGMOD Conference
Emily Caveness, Paul Suganthan G. C., Zhuo Peng, Neoklis Polyzotis, Sudip Roy, Martin Zinkevich
2019 — conf
Continuous Training for Production ML in the TensorFlow Extended (TFX) Platform.
OpML
Denis Baylor, Kevin Haas, Konstantinos Katsiapis, Sammy Leong, Rose Liu, Clemens Mewald, Hui Miao, Neoklis Polyzotis, Mitchell Trott, Martin Zinkevich
2019 — conf
Data Validation for Machine Learning.
SysML
Eric Breck, Neoklis Polyzotis, Sudip Roy, Steven Whang, Martin Zinkevich
2018 J jnl
Data Lifecycle Challenges in Production Machine Learning: A Survey.
SIGMOD Rec.
Neoklis Polyzotis, Sudip Roy, Steven Euijong Whang, Martin Zinkevich
2017 — conf
Data Management Challenges in Production Machine Learning.
SIGMOD Conference
Neoklis Polyzotis, Sudip Roy, Steven Euijong Whang, Martin Zinkevich
2017 J jnl
Safe Exploration for Identifying Linear Systems via Robust Optimization.
CoRR
Tyler Lu, Martin Zinkevich, Craig Boutilier, Binz Roy, Dale Schuurmans
2017 A* conf
TFX: A TensorFlow-Based Production-Scale Machine Learning Platform.
KDD
Denis Baylor, Eric Breck, Heng-Tze Cheng, Noah Fiedel, Chuan Yu Foo, Zakaria Haque, Salem Haykal, Mustafa Ispir, Vihan Jain, Levent Koc, Chiu Yuen Koo, Lukasz Lew, Clemens Mewald, Akshay Naresh Modi, Neoklis Polyzotis, Sukriti Ramesh, Sudip Roy, Steven Euijong Whang, Martin Wicke, Jarek Wilkiewicz, Xin Zhang, Martin Zinkevich
2016 — conf
Deep Learning Games.
NIPS
Dale Schuurmans, Martin Zinkevich
2013 J jnl
The Annual Computer Poker Competition.
AI Mag.
Nolan Bard, John Alexander Hawkin, Jonathan Rubin, Martin Zinkevich
2012 J jnl
An Efficient Optimal-Equilibrium Algorithm for Two-player Game Trees.
CoRR
Michael L. Littman, Nishkam Ravi, Arjun Talwar, Martin Zinkevich
2012 J jnl
No-Regret Learning in Extensive-Form Games with Imperfect Recall
CoRR
Marc Lanctot, Richard G. Gibson, Neil Burch, Martin Zinkevich, Michael H. Bowling
2012 J jnl
On Local Regret
CoRR
Michael Bowling, Martin Zinkevich
2012 A* conf
On Local Regret.
ICML
Michael Bowling, Martin Zinkevich
2011 A* conf
Accelerating Best Response Calculation in Large Extensive Games.
IJCAI
Michael Johanson, Kevin Waugh, Michael H. Bowling, Martin Zinkevich
2011 A conf
Learning to target: what works for behavioral targeting.
CIKM
Sandeep Pandey, Mohamed Aly, Abraham Bagherjeiran, Andrew O. Hatch, Peter Ciccolo, Adwait Ratnaparkhi, Martin Zinkevich
2011 J jnl
Models of Cooperative Teaching and Learning.
J. Mach. Learn. Res.
Sandra Zilles, Steffen Lange, Robert Holte, Martin Zinkevich
2011 J jnl
The lemonade stand game competition: solving unsolvable games.
SIGecom Exch.
Martin Zinkevich, Michael H. Bowling, Michael Wunder
2011 A* conf
Unbiased online active learning in data streams.
KDD
Wei Chu, Martin Zinkevich, Lihong Li, Achint Thomas, Belle L. Tseng
2010 — conf
Parallelized Stochastic Gradient Descent.
NIPS
Martin Zinkevich, Markus Weimer, Alexander J. Smola, Lihong Li
2009 — conf
A Practical Use of Imperfect Recall.
SARA
Kevin Waugh, Martin Zinkevich, Michael Johanson, Morgan Kan, David Schnizlein, Michael H. Bowling
2009 — conf
A demonstration of the Polaris poker system.
AAMAS (2)
Michael H. Bowling, Nicholas Abou Risk, Nolan Bard, Darse Billings, Neil Burch, Joshua Davidson, John Alexander Hawkin, Robert Holte, Michael Johanson, Morgan Kan, Bryce Paradis, Jonathan Schaeffer, David Schnizlein, Duane Szafron, Kevin Waugh, Martin Zinkevich
2009 A* conf
Adaptive bidding for display advertising.
WWW
Arpita Ghosh, Benjamin I. P. Rubinstein, Sergei Vassilvitskii, Martin Zinkevich
2009 — conf
Monte Carlo Sampling for Regret Minimization in Extensive Games.
NIPS
Marc Lanctot, Kevin Waugh, Martin Zinkevich, Michael H. Bowling
2009 — conf
Slow Learners are Fast.
NIPS
Martin Zinkevich, Alexander J. Smola, John Langford
2008 Misc conf
A Fast Way to Produce Optimal Fixed-Depth Decision Trees.
ISAIM
Alireza Farhangfar, Russell Greiner, Martin Zinkevich
2008 A* conf
Teaching Dimensions based on Cooperative Learning.
COLT
Sandra Zilles, Steffen Lange, Robert Holte, Martin Zinkevich
2007 A conf
(Approximate) Subgradient Methods for Structured Prediction.
AISTATS
Nathan D. Ratliff, J. Andrew Bagnell, Martin Zinkevich
2007 A* conf
A New Algorithm for Generating Equilibria in Massive Zero-Sum Games.
AAAI
Martin Zinkevich, Michael H. Bowling, Neil Burch
2007 J jnl
A hierarchy of prescriptive goals for multiagent learning.
Artif. Intell.
Martin Zinkevich, Amy Greenwald, Michael L. Littman
2007 — conf
Computing Robust Counter-Strategies.
NIPS
Michael Johanson, Martin Zinkevich, Michael H. Bowling
2007 — conf
Regret Minimization in Games with Incomplete Information.
NIPS
Martin Zinkevich, Michael Johanson, Michael H. Bowling, Carmelo Piccione
2006 A conf
An Efficient Optimal-Equilibrium Algorithm for Two-player Game Trees.
UAI
Michael L. Littman, Nishkam Ravi, Arjun Talwar, Martin Zinkevich
2006 A* conf
Boosting Expert Ensembles for Rapid Concept Recall.
AAAI
Achim Rettinger, Martin Zinkevich, Michael H. Bowling
2006 A* conf
Maximum margin planning.
ICML
Nathan D. Ratliff, J. Andrew Bagnell, Martin Zinkevich
2006 J jnl
Online algorithms for market clearing.
J. ACM
Avrim Blum, Tuomas Sandholm, Martin Zinkevich
2006 A* conf
Optimal Unbiased Estimators for Evaluating Agent Performance.
AAAI
Martin Zinkevich, Michael H. Bowling, Nolan Bard, Morgan Kan, Darse Billings
2006 A* conf
Prob-Maxn: Playing N-Player Games with Opponent Models.
AAAI
Nathan R. Sturtevant, Martin Zinkevich, Michael H. Bowling
2006 — conf
iLSTD: Eligibility Traces and Convergence Analysis.
NIPS
Alborz Geramifard, Michael H. Bowling, Martin Zinkevich, Richard S. Sutton
2005 — conf
Cyclic Equilibria in Markov Games.
NIPS
Martin Zinkevich, Amy Greenwald, Michael L. Littman
2005 — conf
Response Regret.
AAAI Fall Symposium: Coevolutionary and Coadaptive Systems
Martin Zinkevich
2004 J jnl
Preference Elicitation and Query Learning.
J. Mach. Learn. Res.
Avrim Blum, Jeffrey C. Jackson, Tuomas Sandholm, Martin Zinkevich
2003 A* conf
On polynomial-time preference elicitation with value queries.
EC
Martin Zinkevich, Avrim Blum, Tuomas Sandholm
2003 A* conf
Online Convex Programming and Generalized Infinitesimal Gradient Ascent.
ICML
Martin Zinkevich
2003 A* conf
Preference Elicitation and Query Learning.
COLT
Avrim Blum, Jeffrey C. Jackson, Tuomas Sandholm, Martin Zinkevich
2002 A* conf
Competitive Analysis of the Explore/Exploit Tradeoff.
ICML
John Langford, Martin Zinkevich, Sham M. Kakade
2002 A* conf
Online algorithms for market clearing.
SODA
Avrim Blum, Tuomas Sandholm, Martin Zinkevich
2001 A* conf
Symmetry in Markov Decision Processes and its Implications for Single Agent and Multiagent Learning.
ICML
Martin Zinkevich, Tucker R. Balch