Amir Globerson
I am a postdoc working with Prof. Tommi Jaakkola at CSAIL. Before coming here, I visited the University of Toronto and worked with Sam Roweis.
I received my PhD from the Center for Neural Computation at the Hebrew University in Jerusalem, where I worked with Naftali Tishby and Eilon Vaadia.
Contact
MIT Computer Science and Artificial Intelligence LaboratoryStata Center, Room 32-G482
Cambridge, MA 02139
email: gamir at csail dot mit dot edu
Publications
Journal papers
- Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks
- Gaussian Information Bottleneck
- Euclidean Embedding of Co-Occurrence Data
- Sufficient Dimensionality Reduction
Michael Collins, Amir Globerson, Terry Koo, Xavier Carreras, and Peter Bartlett
Journal of Machine Learning Research. Accepted for publication, 2008.
Gal Chechik, Amir Globerson, Naftali Tishby and Yair Weiss
Journal of Machine Learning Research 6 (Jan), p.165-188, 2005.
Amir Globerson, Gal Chechik, Fernando Pereira and Naftali Tishby
Journal of Machine Learning Research 8 (Oct), p.2265-2295, 2007.
Amir Globerson and Naftali Tishby
Journal of Machine Learning Research 3 (Mar), Special Issue on Variable and Feature Selection, p.1307-1331, 2003.
Conference Proceedings
- Tightening LP Relaxations for MAP using Message Passing
David Sontag, Talya Meltzer. Amir Globerson, Tommi Jaakkola and Yair Weiss
Uncertainty in Artificial Intelligence (UAI). Helsinki, Finland. 2008.
Received the best paper award.
- Fixing max-product: Convergent message passing algorithms for MAP LP-relaxations
Amir Globerson , Tommi Jaakkola
Advances in Neural Information Processing Systems (NIPS) 21. Vancouver, Canada. 2007.
- Convex Learning with Invariances
Choon Hui Teo, Amir Globerson , Sam Roweis and Alex Smola
Advances in Neural Information Processing Systems (NIPS) 21. Vancouver, Canada. 2007.
- Convergent Propagation Algorithms via Oriented Trees
Amir Globerson and Tommi Jaakkola
Uncertainty in Artificial Intelligence (UAI), 2007.
Received the Best Paper Award
- Structured Prediction Models via The Matrix-Tree Theorem
Terry Koo, Amir Globerson, Xavier Carreras and Michael Collins
Empirical Methods in Natural Language Processing (EMNLP), 2007.
- Exponentiated Gradient Algorithms for Log-Linear Structured Prediction
Amir Globerson, Terry Koo, Xavier Carreras and Michael Collins
Proceedings of the Interational Conference on Machine Learning (ICML) , 2007.
- Approximate Inference Using Conditional Entropy Decompositions
Amir Globerson and Tommi Jaakkola
The 11th International Workshop on Artificial Intelligence and Statistics (AISTATS). Puerto-Rico 2007.
- Visualizing Pairwise Similarity via Semidefinite Programming
Amir Globerson and Sam Roweis
The 11th International Workshop on Artificial Intelligence and Statistics (AISTATS). Puerto-Rico 2007.
- Approximate Inference Using Planar Graph Decomposition
Amir Globerson , Tommi Jaakkola
Advances in Neural Information Processing Systems (NIPS) 20. Vancouver, Canada. 2006.
- Discriminative Learning via Semidefinite Probabilities
Koby Crammer, Amir Globerson
Proceedings of Uncertainty in Artificial Intelligence (UAI) , Boston, MA. 2006.
- Nightmare at Test Time: Robust Learning by Feature Deletion
Amir Globerson, Sam Roweis
Proceedings of the Interational Conference on Machine Learning (ICML) , Pittsburgh, PA. 2006.
- Metric Learning by Collapsing Classes
Amir Globerson, Sam Roweis
Advances in Neural Information Processing Systems (NIPS) 19. Vancouver, Canada. 2005.
- Euclidean Embedding of Co-occurrence data
Amir Globerson, Gal Chechik, Fernando Pereira and Naftali Tishby
Advances in Neural Information Processing Systems (NIPS) 18. Vancouver, Canada. 2004.
Received the Outstanding Student Paper Award.
- Distributed Latent Variable Models of Lexical Co-occurrences
John Blitzer, Amir Globerson and Fernando Pereira
Tenth International Workshop on Artificial Intelligence and Statistics (AISTATS). Barbados 2005.
- The Minimum Information Principle in Discriminative Learning
- Gaussian Information Bottleneck
Amir Globerson and Naftali Tishby
Uncertainty in Artificial Inteligence (UAI). Banff ,Canada 2004.
Gal Chechik, Amir Globerson, Naftali Tishby and Yair Weiss
Advances in Neural Information Processing Systems (NIPS) 17.Vancouver, Canada. 2003.
- Sufficient Dimensionality Reduction with Irrelevance Statistics.
Amir Globerson, Gal Chechik, and Naftali Tishby
Uncertainty in Artificial Inteligence (UAI). Acapulco, Mexico. 2003.
- Sufficient Dimensionality Reduction - A Novel Analysis Principle
Amir Globerson and Naftali Tishby
International Conference on Machine Learning (ICML). Sydney, Australia. 2002.
- Groups Redundancy Measures Reveal Redundancy Reduction Along the Auditory Pathway
Gal Chechik, Amir Globerson, Michael Anderson, Eric Young, Israel Nelken and N. Tishby
Advances in Neural Information Processing Systems NIPS-15. Vancouver Canada, 2001.
PhD Thesis
- The Minimum Information Principle in Learning and Neural Data Analysis
The Hebrew University, Jerusalem, 2005. Advisors: Prof. N. Tishby and Prof. E. Vaadia
Technical Reports and Abstracts
- On the Optimality of the Gaussian Information Bottleneck Curve
Amir Globerson and Naftali Tishby
Hebrew University Technical Report, 2004
- Distributional Clustering of Movements Based on Neural Responses
Amir Globerson, Gal Chechik, Orna Steinberg, Eilon Vaadia and Natali Tishby.
Hebrew University Technical Report, 2004
- Information Bounds on Vectors with Applications to Nonstationary and Population Coding
Amir Globerson, Eran Stark, Ron Paz, Eilon Vaadia and Naftali Tishby.
Abstracts of papers presetned at the CSHL 2004 Meeting on Computational and Systems Neuroscience (COSYNE)
Teaching
- 2003-2005 : Teaching the course Computation, Information, and Learning I
- 2000-2003 : TA in Introduction to linear systems