I am a researcher in machine learning and artificial intelligence. My work is focused on advancing AI and developing novel algorithms to solve complex problems in diverse fields such as computer vision, bioinformatics, smart manufacturing, and finance. I have extensive experience in deep learning, model evaluation and calibration, ensemble learning, transfer learning, extreme classification, and time series modeling. Recently I have been interested in enhancing deep learning with reasoning capabilities and integrating symbolic knowledge into deep learning models.
Selected Publications
For a full list see my google scholar profile.
Hopper: Multi-hop transformer for spatiotemporal reasoning
Honglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf
International Conference on Learning Representation (ICLR, '21)
Label Filters for Large Scale Multilabel Classification
Alexandru Niculescu-Mizil, Ehsan Abbasnejad
Proceedings of the 20th International Conference on AI and Statistics (AISTATS '17)
[Code]
On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models
Adarsh Prasad, Alexandru Niculescu-Mizil, Pradeep Ravikumar
Proceedings of the 30th Neural Information Processing Systems (NIPS '17)
Practical Applications of Sparse Modeling
Irina Rish, Guillermo A. Cecchi, Aurelie Lozano, Alexandru Niculescu-Mizil, eds.
The MIT Press, 2014
Climate Informatics
Claire Monteleoni, Gavin A. Schmidt,
Francis Alexander, Alexandru Niculescu-Mizil, et al.
Computational Intelligent Data Analysis for Sustainable Development, 2013.
Developing Predictive Models Using Electronic Medical Records: Challenges and Pitfalls
Chris Paxton, Alexandru Niculescu-Mizil, Suchi Saria
American Medical Informatics Association (AMIA '13)
A Binary Classification Framework for Two Stage Multiple Kernel Learning
Abhishek Kumar, Alexandru Niculescu-Mizil, Koray Kavukcuoglu, Hal Daume III
Proceedings of the 29th International Conference on Machine Learning (ICML '12)
Bayesian Models for Large-Scale Hierarchical Classification
Siddharth Gopal, Yiming Yang, Bing Bai, Alexandru Niculescu-Mizil
Proceedings of the 26th Neural Information Processing Systems (NIPS '12)
[Code]
Learning Temporal Graphs for Relational Time-Series Analysis
Yan Liu, Alexandru Niculescu-Mizil, Aurelie Lozano, Young Lu
Proceedings of the 27th International Conference on Machine Learning (ICML '10)
Temporal Graphical Models for Cross-Species Gene Regulatory Network Discovery
Yan Liu, Alexandru Niculescu-Mizil, Aurelie Lozano, Young Lu
Proceedings of the 9th International Conference on Computational Systems Bioinformatics (CSB '10)
Regret Bounds for Sleeping Experts and Bandits
Robert Kleinberg, Alexandru Niculescu-Mizil, Yogeshwer Sharma
Machine Learning, 2010
Winning the KDD Cup Orange Challenge with Ensemble Selection
Alexandru Niculescu-Mizil, et al.
Journal of Machine Learning Research, 2009
Spatial-temporal Causal Modeling for Climate Change Attribution
Aurelie Lozano, Hongfei Li, Alexandru Niculescu-Mizil, Yan Liu, Claudia Perlich, Jonathan Hosking, Naoki Abe
Proceedings of the 15th International Conference on Knowledge Discovery and Data Mining (KDD '09)
Topic-Link LDA: Joint Models of Topic and Author Community
Yan Liu, Alexandru Niculescu-Mizil, Wojciech Gryc
Proceedings of the 26th International Conference on Machine Learning (ICML '09)
Regret Bounds for Sleeping Experts and Bandits
Robert Kleinberg, Alexandru Niculescu-Mizil, Yogeshwer Sharma
Proceedings of the 21st Annual Conference on Learning Theory (COLT '08)
Best student paper award
Inductive Transfer for Bayesian Network Structure Learning
Alexandru Niculescu-Mizil, Rich Caruana
Proceedings of the 11th International Conference on AI and Statistics (AISTATS '07)
Learning Graphical Model Structure using L1-Regularization Paths
Mark Schmidt, Alexandru Niculescu-Mizil, Kevin Murphy
Proceedings of the 22nd Conference on Artificial Intelligence (AAAI '07)
An Empirical Comparison of Supervised Learning Algorithms
Rich Caruana, Alexandru Niculescu-Mizil
Proceedings of the 23rd International Conference on Machine Learning (ICML '06)
Model Compression
Cristian Bucila, Rich Caruana, Alexandru Niculescu-Mizil
Proceedings of the 12th International Conference on Knowledge Discovery and Data Mining (KDD '06)
Predicting Good Probabilities With Supervised Learning
Alexandru Niculescu-Mizil, Rich Caruana
Proceedings of the 22nd International Conference on Machine Learning (ICML '05)
Distinguished student paper award
Ensemble Selection from Libraries of Models
Rich Caruana, Alexandru Niculescu-Mizil, Geoff Crew, Alex Ksikes
Proceedings of the 21st International Conference on Machine Learning (ICML '04)