Alex's Home Page IBM T.J. Watson Research Center 1101 Kitchawan Road, Route 134 Yorktown Heights, NY 10598 Tel. +1(914)945-1164 alexnic at gmail com

    I am a Herman Goldstine Postoctoral Fellow at IBM T.J. Watson Research Lab. My main area of research is Machine Learning. I am currently working on transfer learning, ensemble learning, predicting calibrated probabilities with supervised learning and on-line learning. I am also interested in unsupervised/semi-supervised learning and learning from weaker feedback (e.g. multi-instance learning, multi label learning, learning from preferences).

• Journal papers:
  • Robert Kleinberg, Alexandru Niculescu-Mizil, Yogeshwer Sharma: Regret Bounds for Sleeping Experts and Bandits - Machine Learning Journal, to appear.
  • Alexandru Niculescu-Mizil, et al. : Winning the KDD Cup Orange Challenge with Ensemble Selection - Journal of Machine Learning Research, to appear.
  • Tom Fawcett, Alexandru Niculescu-Mizil: PAV and the ROC Convex Hull - Machine Learning, Technical Note, Vol. 68, No. 1, July 2007, pp. 97-106 [Springer Link].
• Peer reviewed conference papers:
  • Yan Liu, Alexandru Niculescu-Mizil, Aurelie Lozano, Young Lu: Learning Temporal Graphs for Relational Time-Series Analysis - Proceedings of the 27th International Conference on Machine Learning (ICML `10), to appear.
  • Aurelie Lozano, Hongfei Li, Alexandru Niculescu-Mizil, Yan Liu, Claudia Perlich, Jonathan Hosking, Naoki Abe: Spatial-temporal Causal Modeling for Climate Change Attribution - Proceedings of the 15th International Conference on Knowledge Discovery and Data Mining (KDD `09).
  • Yan Liu, Alexandru Niculescu-Mizil, Wojciech Gryc: Topic-Link LDA: Joint Models of Topic and Author Community - Proceedings of the 26th International Conference on Machine Learning (ICML `09).
  • Robert Kleinberg, Alexandru Niculescu-Mizil, Yogeshwer Sharma: Regret Bounds for Sleeping Experts and Bandits - Proceedings of the 21st Annual Conference on Learning Theory (COLT `08). Best student paper award.
  • Alexandru Niculescu-Mizil, Rich Caruana: Inductive Transfer for Bayesian Network Structure Learning - Proceedings of the 11th International Conference on AI and Statistics (AISTATS `07).
  • David B. Skalak, Alexandru Niculescu-Mizil, Rich Caruana: Classifier Loss under Metric Uncertainty - Proceedings of the 18th European Conference on Machine Learning (ECML `07).
  • Mark Schmidt, Alexandru Niculescu-Mizil, Kevin Murphy: Learning Graphical Model Structure using L1-Regularization Paths - Proceedings of the 22nd Conference on Artificial Intelligence (AAAI `07).
  • Rich Caruana, Alexandru Niculescu-Mizil: An Empirical Comparison of Supervised Learning Algorithms - Proceedings of the 23rd International Conference on Machine Learning (ICML `06). Top and bottom of the scales used to calculate normalized scores.
  • Cristian Bucila, Rich Caruana, Alexandru Niculescu-Mizil: Model Compression - Proceedings of the 12th International Conference on Knowledge Discovery and Data Mining (KDD `06).
  • Rich Caruana, Art Munson, Alexandru Niculescu-Mizil: Getting the Most Out of Ensemble Selection - Proceedings of the 6th International Conference on Data Mining (ICDM `06). Full-length version.
  • Alexandru Niculescu-Mizil, Rich Caruana: Predicting Good Probabilities With Supervised Learning - Proceedings of the 22nd International Conference on Machine Learning (ICML `05). Distinguished student paper award.
  • Alexandru Niculescu-Mizil, Rich Caruana: Obtaining Calibrated Probabilities from Boosting - Proceedings of the 21st Conference on Uncertainty in Artificial Intelligence (UAI `05).
  • Rich Caruana, Alexandru Niculescu-Mizil, Geoff Crew, Alex Ksikes: Ensemble Selection from Libraries of Models - Proceedings of the 21st International Conference on Machine Learning (ICML `04).
  • Rich Caruana, Alexandru Niculescu-Mizil: Data Mining in Metric Space: An Empirical Analysis of Supervised Learning Performance Criteria - Proceedings of the 10th International Conference on Knowledge Discovery and Data Mining (KDD `04).
• Workshop papers:
  • Alexandru Niculescu-Mizil: Multi-Armed Bandits with Betting - On-line Learning with Limited Feedback (COLT 09 Workshop).
  • Alexandru Niculescu-Mizil, Rich Caruana: Learning the Structure of Related Tasks - Inductive Transfer: 10 Years Later Workshop (ITWS `05).
  • Rich Caruana, Alexandru Niculescu-Mizil: An Empirical Evaluation of Supervised Learning for ROC Area - First Workshop of ROC Analysis in AI (ROCAI `04).
• Technical reports:
  • Rich Caruana, Art Munson, Alexandru Niculescu-Mizil: Getting the Most Out of Ensemble Selection - Cornell University TR2006-2045, 2006. Full-length version of the ICDM `06 paper.
  • Rich Caruana, Alexandru Niculescu-Mizil: An Empirical Comparison of Supervised Learning Algorithms Using Different Performance Metrics - Cornell University TR2005-1973, 2005.

• NESCAI : North East Student Colloquium on Artificial Intelligence.
• Machine Learning at Cornell.

• Cornell CS & friends ice hockey.
• My ex-office mates ( Eric , Jeff and Filip ).
• The cleaning services startup of my best friend Andrei.
• The other startup of Andrei.