Mohammad Ghavamzadeh

Senior Analytics Researcher

BigData Experience Lab, San Jose

Mohammad’s research interests lie primarily in machine learning and artificial intelligence, with emphasis on decision-making under uncertainty using principled mathematical tools from probability theory, decision theory, and statistics.

He received his Ph.D. degree in computer science from the University of Massachusetts Amherst in 2005. He was a Postdoctoral Fellow at the Department of Computing Science at the University of Alberta from 2005 to 2008. He was a Researcher at the Institut National de Recherche en Informatique et en Automatique (INRIA) in Lille, France from 2008 to 2013. In October 2013, he joined Adobe as a senior analytics researcher to work in the area of digital marketing.

He is on the editorial board of the Machine Learning Journal (MLJ) since 2011 and has reviewed for the Journal of Machine Learning Research (JMLR), Journal of Artificial Intelligence Research (JAIR), Journal of Operations Research, IEEE Transactions on Automatic Control, Journal of Autonomous Agents and Multi-Agent Systems (JAAMAS), NeuroComputing, Journal of Aunomous Robots, and International Journal of Robotics Research (IJRR).

He has been an Area Chair at NIPS 2013 and IJCAI 2011; a Program Committee member at ICML 2006-2014, AAAI 2007, 2008, 2011, UAI 2012, and ECML 2010, 2012; and a Reviewer for NIPS 2006-2012, AISTATS 2009, 2011, 2012, AAAI 2005, IJCAI 2007, and COLT 2008.

For his detailed CV including a list of publications, please click here.

 

My Publications

Model-Independent Online Learning for Influence Maximization

Vaswani, S., Kveton, B., Wen, Z., Ghavamzadeh, M., Lakshmanan, L., Schmidt, M. (Aug. 6, 2017)
Proceedings of International Conference on Machine Learning (ICML) 2017

Online Learning to Rank in Stochastic Click Models

Zoghi, M., Tunys, T., Ghavamzadeh, M., Kveton, B., Szepesvari, C., Wen, Z. (Aug. 6, 2017)
Proceedings of International Conference on Machine Learning (ICML) 2017

Importance of Recommendation Policy Space in Addressing Click Sparsity in Personalized Advertisement Display

Chaudhuri, S., Theocharous, G., Ghavamzadeh, M. (Jul. 17, 2017)
International Conference on Machine Learning and Data Mining in Pattern Recognition

Automated Data Cleansing through Meta-Learning

Gemp, I., Theocharous, G., Ghavamzadeh, M. (Feb. 4, 2017)
Innovative Applications of Artificial Intelligence (IAAI)

Predictive Off-Policy Policy Evaluation for Nonstationary Decision Problems, with Applications to Digital Marketing

Thomas, P., Theocharous, G., Ghavamzadeh, M., Durugkar, I., Brunskill, E. (Feb. 4, 2017)
Innovative Applications of Artificial Intelligence (IAAI)

Safe Policy Improvement by Minimizing Robust Baseline Regret

Petrik, M., Ghavamzadeh, M., Chow, Y. (Dec. 1, 2016)
Thirtieth Annual Conference on Advances in Neural Information Processing Systems (NIPS-2016), 2016.

Variance-constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs

Prashanth, L., Ghavamzadeh, M. (Nov. 1, 2016)
Machine Learning Journal (MLJ), 105:3:367-417, 2016 (DOI: 10.1007/s10994-016-5569-5)

Stochastic Video Prediction with Conditional Density Estimation

Shu, R., Brofos, J., Zhang, F., Bui, H., Ghavamzadeh, M., Kochenderfer, M. (Oct. 1, 2016)
Workshop on “Action and Anticipation for Visual Learning”, Fourteenth European Conference on Computer Vision (ECCV-2016), Amsterdam, The Netherlands, October, 2016.

Graphical Model Sketch

Kveton, B., Bui, H., Ghavamzadeh, M., Theocharous, G., Muthukrishnan, S., Sun, S. (Sep. 19, 2016)
European Conference on Machine Learning and Knowledge Discovery in Databases

Regularized Policy Iteration for Nonparametric Function Spaces

Farahmand, A., Ghavamzadeh, M., Szepesvari, C., Mannor, S. (Aug. 1, 2016)
Journal of Machine Learning Research (JMLR), 17(139):1-66, 2016

Bayesian Policy Gradient and Actor-Critic Algorithms

Ghavamzadeh, M., Engel, Y., Valko, M. (Jul. 1, 2016)
Journal of Machine Learning Research (JMLR), 17(66):1-53, 2016

Analysis of Classification-based Policy Iteration Algorithms

Lazaric, A., Ghavamzadeh, M., Munos, R. (Jul. 1, 2016)
Journal of Machine Learning Research (JMLR), 17(19):1-30, 2016.

Proximal Gradient Temporal Difference Learning Algorithms

Liu, B., Liu, J., Ghavamzadeh, M., Mahadevan, S., Petrik, M. (Jul. 1, 2016)
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-2016), New York City, NY, 2016.

Optimally Robust Policy Improvement with Baseline Guarantees

Petrik, M., Chow, Y., Ghavamzadeh, M. (Jun. 1, 2016)
Workshop on “Reliable Machine Learning in the Wild”, Thirty-Third International Conference on Machine Learning (ICML- 2016), New York City, NY, June 2016.

A Ranking Approach to Address the Click Sparsity Problem in Personalized Ad Recommendation

Chaudhuri, S., Theocharous, G., Ghavamzadeh, M. (Dec. 11, 2015)
Workshop: Machine Learning for eCommerce (NIPS) 2015.

Bayesian Reinforcement Learning: A Survey

Ghavamzadeh, M., Mannor, S., Pineau, J., Tamar, A. (Dec. 1, 2015)
Foundations and Trends in Machine Learning, 8(5-6):359-483, 2015 (DOI: 10.1561/2200000049).

Policy Gradient for Coherent Risk Measures

Tamar, A., Chow, Y., Ghavamzadeh, M., Mannor, S. (Dec. 1, 2015)
Proceedings of the Twenty-Ninth Annual Conference on Advances in Neural Information Processing Systems (NIPS-2015), pp. 1468-1476, 2015.

Approximate Modified Policy Iteration and its Application to the Game of Tetris

Scherrer, B., Ghavamzadeh, M., Gabillon, V., Lesner, B., Geist, M. (Aug. 1, 2015)
Journal of Machine Learning Research (JMLR), 16:1629-1676, 2015.

Finite-Sample Analysis of Proximal Gradient TD Algorithms

Liu, B., Liu, J., Ghavamzadeh, M., Mahadevan, S., Petrik, M. (Aug. 1, 2015)
winner of the Facebook best student paper award Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence (UAI-2015), pp. 504-513, Amsterdam, Netherlands, 2015.

Maximum Entropy Semi-Supervised Inverse Reinforcement Learning

Audiffren, J., Valko, M., Lazaric, A., Ghavamzadeh, M. (Aug. 1, 2015)
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-2015), pp. 3315-3321, Buenos Aires, Argentina, 2015.

High Confidence Policy Improvement

Thomas, P., Theocharous, G., Ghavamzadeh, M. (Jul. 1, 2015)
International Conference on Machine Learning (ICML) 2015.

Personalized Ad Recommendation Systems for Life-Time Value Optimization with Guarantees.

Theocharous, G., Thomas, P., Ghavamzadeh, M. (Jul. 1, 2015)
International Joint Conference on Artificial Intelligence (IJCAI) 2015.

Ad Recommendation Systems for Life-Time Value Optimization

Theocharous, G., Thomas, P., Ghavamzadeh, M. (May. 1, 2015)
Workshop on Ad Targeting at Scale (WWW) 2015.

Classification-based Approximate Policy Iteration

Farahmand, A., Precup, D., Barreto, A., Ghavamzadeh, M. (May. 1, 2015)
IEEE Transactions on Automatic Control (TAC), 60(11): 2989- 2993, 2015.

Improved Learning Complexity in Combinatorial Pure Exploration Bandits

Gabillon, V., Lazaric, A., Ghavamzadeh, M., Ortner, R., Bartlett, P. (May. 1, 2015)
Proceedings of the Nine- teenth International Conference on Artificial Intelligence and Statistics (AISTATS-2016), pp. 1004-1012, Cadiz, Spain, 2016.

High Confidence Off-Policy Evaluation

Thomas, P., Theocharous, G., Ghavamzadeh, M. (Jan. 1, 2015)
Association for the Advancement of Artificial Intelligence (AAAI) 2015.

Algorithms for CVaR Optimization in MDPs

Chow, Y., Ghavamzadeh, M. (Dec. 1, 2014)
Proceedings of the Twenty-Eighth Annual Conference on Advances in Neural Information Processing Systems (NIPS-2014), pp. 3509-3517, 2014.

Constrained Stochastic Optimal Control with a Baseline Performance Guarantee

Chow, Y., Ghavamzadeh, M. (Dec. 1, 2014)
Workshop on “From Bad Models to Good Policies”, Twenty-Eighth Annual Conference on Advances in Neural Information Processing Systems (NIPS-2014), Montreal, Canada, December 2014.

Actor-Critic Algorithms for Risk-Sensitive MDPs

Prashanth, L., Ghavamzadeh, M. (Dec. 1, 2013)
Selected for Oral Presentation (%1.4 acceptance – 20 out of 1420 submissions) Proceedings of the Twenty-Seventh Annual Conference on Advances in Neural Information Processing Systems (NIPS-2013), pp. 252-260, 2013.

Approximate Dynamic Programming Finally Performs Well in the Game of Tetris

Gabillon, V., Ghavamzadeh, M., Scherrer, B. (Dec. 1, 2013)
Proceedings of the Twenty-Seventh Annual Conference on Advances in Neural Information Processing Systems (NIPS-2013), pp. 1754-1762, 2013.