Publications

On the Inductive Bias of Neural Networks for Learning Read-once DNFs 

Ido Bronstein, Alon Brutzkus, Amir Globerson

The Conference on Uncertainty in Artificial Intelligence (UAI) 2022.

Efficient Learning of CNNs using Patch Based Features 

Alon Brutzkus, Amir Globerson, Eran Malach, Alon Regev Netser ,Shai Shalev-Shwartz 

 International Conference on Machine Learning (ICML), 2022.

Learning to Retrieve Passages without Supervision

Ori Ram, Gal Shachaf, Omer Levy, Jonathan Berant, Amir Globerson

The North American Chapter of the Association for Computational Linguistics (NAACL), 2022.

On the Implicit Bias of Gradient Descent for Temporal Extrapolation

Edo Cohen-Karlik, Avichai Ben David, Nadav Cohen, Amir Globerson

Conference on Artificial Intelligence and Statistics (AISTATS), 2022.

Object-Region Video Transformers

Roei Herzig, Elad Ben-Avraham, Karttikeya Mangalam, Amir Bar, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson

Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

 

 

DETReg: Unsupervised Pretraining with Region Priors for Object Detection

Amir Bar, Xin Wang, Vadim Kantorov, Colorado J Reed, Roei Herzig, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson

Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

 

 

A Theoretical Analysis of Fine-tuning with Linear Teachers

Gal Shachaf, Alon Brutzkus, Amir Globerson

Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021).

BERTese: Learning to Speak to BERT

Adi HavivJonathan Berant, Amir Globerson

European Chapter of the Association for Computational Linguistics (EACL), 2021: 3618-3623.

Compositional Video Synthesis with Action Graphs

Amir Bar , Roei Herzig, Xiaolong Wang,Anna Rohrbach, Gal Chechik,Trevor Darrell, Amir Globerson

International Conference on Machine Learning (ICML), 2021.

 

Towards Understanding Learning in Neural Networks with Linear Teachers

Roy Sarussi, Alon Brutzkus, Amir Globerson

International Conference on Machine Learning (ICML), 2021.

 

On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent

Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake Woodworth, Nathan Srebro, Amir Globerson, Daniel Soudry

International Conference on Machine Learning (ICML), 2021.

An Optimization and Generalization Analysis for Max-Pooling Networks

 Uncertainty in Artificial Intelligence (UAI) 2021

Few-Shot Question Answering by Pretraining Span Selection

Ori Ram, Yuval Kirstain, Jonathan Berant, Amir Globerson amd Omer Levy

Association for Computational Linguistics (ACL) 2021 

Learning Canonical Representations for Scene Graph to Image Generation

Roei Herzig, Amir Bar, Huijuan Xu, Gal Chechik, Trevor Darrell, Amir Globerson.

ECCV 2020


 

Learning Object Permanence from Video

Aviv Shamsian, Ofri Kleinfeld, Amir Globerson, Gal Chechik.

ECCV 2020 

 

Regularizing Towards Permutation Invariance In Recurrent Models
Edo Cohen, Avichai Ben David and Amir Globerson
Advanced in Neural Information Processing Systems (NeurIPS) 2020

A Simple and Effective Model for Answering Multi-span Questions
Elad Segal, Avia Efrat, Mor Shoham, Amir Globerson and Jonathan Berant
Empirical Mehtods in Natural Language Processing (EMNLP) 2020

Pre-training Mention Representations in Coreference Models
Yuval Varkel and Amir Globerson
Empirical Mehtods in Natural Language Processing (EMNLP) 2020

Optimal Strategies Against Generative Attacks
Roy Mor, Erez Peterfreund, Matan Gavish, Amir Globerson
International Conference on Learning Representations (ICLR) 2020.

Differentiable scene graphs
Moshiko Raboh, Roei Herzig, Gal Chechik, Jonathan Berant, Amir Globerson
The IEEE Winter Conference on Applications of Computer Vision (WACV) 2020

Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem
Alon Brutzkus and Amir Globerson
International Conference on Machine Learning (ICML) 2019.

Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing
Tal Schuster, Ori Ram, Regina Barzilay, Amir Globerson
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) 2019.

Explaining Queries over Web Tables to Non-Experts
Jonathan Berant, Daniel Deutsch, Amir Globerson, Tova Milo and Tomer Wolfson
International Conference on Data Engineering (ICDE) 2019.

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
Roei Herzig, Moshiko Raboh, Gal Chechik, Jonathan Berant and Amir Globerson
Advanced in Neural Information Processing Systems (NIPS), 2018.

Learning to Optimize Combinatorial Functions
Nir Rosenfeld, Eric Balkanski, Amir Globerson and Yaron Singer
International Conference on Machine Learning (ICML) 2018

Predict and Constrain: Modeling Cardinality in Deep Structured Prediction
Nataly Brukhim and Amir Globerson
International Conference on Machine Learning (ICML) 2018

Weakly-supervised Semantic Parsing with Abstract Examples
Omer Goldman, Veronica Latcinnik, Udi Naveh, Amir Globerson and Jonathan Berant
Association for Computational Linguistics (ACL) 2018

SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data
Alon Brutzkus, Amir Globerson, Eran Malach and Shai Shalev-Shwartz
International Conference on Learning Representations (ICLR), 2018.

Semi-Supervised Learning with Competitive Infection Models
Nir Rosenfeld and Amir Globerson
Artificial Intelligence and Statistics (AISTATS), 2018.

Robust Conditional Probabilities
Yoav Wald and Amir Globerson
Advanced in Neural Information Processing Systems (NIPS), 2017.

Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
Alon Brutzkus and Amir Globerson
International Conference on Machine Learning (ICML), 2017

Learning Infinite-Layer Networks: Beyond the Kernel Trick
Roi Livni, Daniel Carmon and Amir Globerson
International Conference on Machine Learning (ICML), 2017

Effective Semisupervised Learning on Manifolds
Amir Globerson, Roi Livni and Shai Shalev-Shwartz
Conference on Computational Learning Theory (COLT), 2017

Optimal Tagging with Markov Chain Optimization
Nir Rosenfeld and Amir Globerson
NIPS Advances in Neural Information Processing Systems (NIPS) 30, 2016.

Collective Entity Resolution with Multi-Focal Attention
Amir Globerson, Nevena Lazic, Soumen Chakrabarti, Amarnag Subramanya, Michael Ringgaard and Fernando Pereira
Association for Computational Linguistics (ACL) 2016

Improper Deep Kernels
Uri Heinemann, Roi Livni, Elad Eban, Gal Elidan, Amir Globerson
Artificial Intelligence and Statistics (AISTATS) 2016

Discriminative Learning of Infection Models
Nir Rosenfeld, Mor Nitzan and Amir Globerson
ACM International Conference on Web Search and Data Mining (WSDM), 2016

Template kernels for dependency parsing
Hillel Taub-Tabib, Yoav Goldberg and Amir Globerson
Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) 2015

How Hard is Inference for Structured Prediction?
Amir Globerson, Tim Roughgarden, David Sontag and Cafer Yildirim
International Conference on Machine Learning (ICML) 2015

Tightness Results for Local Consistency Relaxations in Continuous MRFs
Yoav Wald and Amir Globerson
Uncertainty in Artificial Intelligence (UAI) 2014

Lifted Message Passing as Reparametrization of Graphical Models
Martin Mladenov, Kristian Kersting and Amir Globerson
Uncertainty in Artificial Intelligence (UAI) 2014

Discrete Chebyshev Classifiers
Elad Eban, Elad Mezuman and Amir Globerson
International Conference on Machine Learning (ICML) 2014
Runner up for Best Paper.

Inferning with High Girth Graphical Models
Uri Heineman and Amir Globerson
International Conference on Machine Learning (ICML) 2014

Steps to excellence: Simple inference with refined scoring of dependency trees
Y. Zhang, T. Lei, R. Barzilay, T. Jaakkola, and A. Globerson
Association for Computational Linguistics (ACL) 2014

Efficient Lifting of MAP LP Relaxations Using k-Locality
Martin Mladenov, Amir Globerson and Kristian Kersting
Artificial Intelligence and Statistics (AISTATS) 2014

Learning Structured Models with the AUC Loss and Its Generalizations
Nir Rosenfeld, Ofer Meshi, Danny Tarlow and Amir Globerson
Artificial Intelligence and Statistics (AISTATS) 2014

Higher Order Matching for Consistent Multiple Target Tracking
Chetan Arora and Amir Globerson
International Conference on Computer Vision (ICCV) 2013

Tighter Linear Program Relaxations for High Order Graphical Models
Elad Mezuman, Daniel Tarlow, Amir Globerson and Yair Weiss
Uncertainty in Artificial Intelligence (UAI) 2013

Learning Max-Margin Tree Predictors
Ofer Meshi, Elad Eban, Gal Elidan and Amir Globerson
Uncertainty in Artificial Intelligence (UAI) 2013

Transfer Learning for Constituency-Based Grammars
Yuan Zhang, Amir Globerson and Regina Barzilay
Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2013.

Vanishing Component Analysis
Roi Livni, David Lehavi, Sagi Schein, Hila Nachlieli, Shai Shalev Shwartz and Amir Globerson
International Conference on Machine Learning (ICML), 2013.
Received the Best Paper Award.

The Pairwise Piecewise-Linear Embedding for Efficient Non-Linear Classification
Ofir Pele, Ben Taskar, Amir Globerson, Michael Werman
International Conference on Machine Learning (ICML), 2013.

Convergence Rate Analysis of MAP Coordinate Minimization Algorithms
Supplementary

Ofer Meshi, Tommi Jaakkola and Amir Globerson
Advances in Neural Information Processing Systems (NIPS) 25, 2012.

Improved Parsing and POS Tagging Using Inter-Sentence Consistency Constraints
Alexander Rush, Roi Reichart, Michael Collins and Amir Globerson
Empirical Methods in Natural Language Processing (EMNLP), 2012.

Learning to Map into a Universal POS Tagset
Yuan Zhang, Roi Reichart, Regina Barzilay and Amir Globerson
Empirical Methods in Natural Language Processing (EMNLP), 2012.

Selective Sharing for Multilingual Dependency Parsing
Tahira Naseem, Regina Barzilay and Amir Globerson
Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2012.

Learning the Experts for Online Sequence Prediction
Elad Eban, Aharon Birnbaum, Shai Shalev Shwartz and Amir Globerson
Proceedings of the International Conference on Machine Learning (ICML), 2012.

A Simple Geometric Interpretation of SVM using Stochastic Adversaries
Roi Livni, Koby Crammer and Amir Globerson
Artificial Intelligence and Statistics (AISTATS), 2012.

What Cannot be Learned with Bethe Approximations.
Uri Heinemann and Amir Globerson
Uncertainty in Artificial Intelligence (UAI), 2011.

An Alternating Direction Method for Dual MAP LP Relaxation.
Ofer Meshi and Amir Globerson
European Conference on Machine Learning (ECML), 2011.

More data means less inference: A pseudo-max approach to structured learning.
David Sontag, Ofer Meshi, Tommi Jaakkola and Amir Globerson
Advances in Neural Information Processing Systems (NIPS) 23, 2010.

Learning Efficiently with Approximate Inference via Dual Losses.
Ofer Meshi, David Sontag, Tommi Jaakkola and Amir Globerson
The 27th International Conference on Machine Learning (ICML), 2010.

Learning Bayesian Network Structure using LP Relaxations
Tommi Jaakkola, David Sontag, Amir Globerson and Marina Meila
The International Workshop on Artificial Intelligence and Statistics (AISTATS), 2010.

An LP view of the M best problem
Menachem Fromer and Amir Globerson
Advances in Neural Information Processing Systems (NIPS) 22, 2009.
Received the Outstanding Student Paper Award.

Convexifying the Bethe Free Energy
Ofer Meshi, Ariel Jaimovich, Amir Globerson and Nir Friedman
Proceedings of Uncertainty in Artificial Intelligence (UAI). Montreal, Canada. 2009.

Convergent message passing algorithms - a unifying view
Talya Meltzer, Amir Globerson and Yair Weiss
Proceedings of Uncertainty in Artificial Intelligence (UAI). Montreal, Canada. 2009.

Clusters and Coarse Partitions in LP Relaxations
David Sontag, Amir Globerson and Tommi Jaakkola
Advances in Neural Information Processing Systems (NIPS) 21. Vancouver, Canada. 2008.

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) 20. Vancouver, Canada. 2007.

Convex Learning with Invariances
Choon Hui Teo, Amir Globerson , Sam Roweis and Alex Smola
Advances in Neural Information Processing Systems (NIPS) 20. 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) 19. 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) 18. 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) 17. 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
Amir Globerson and Naftali Tishby
Uncertainty in Artificial Inteligence (UAI). Banff ,Canada 2004.


 

Gaussian Information Bottleneck
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) 14. Vancouver  Canada,  2001.