Recent Publications
​
​
EMNLP 21 Publications:
​
Transformer feed-forward layers are key-value memories
Mor Geva, Roei Schuster, Jonathan Berant, Omer Levy
Empirical Methods in Natural Language Processing (EMNLP), 2021
​
​
Value-aware approximate attention
Ankit Gupta, Jonathan Berant
Empirical Methods in Natural Language Processing (EMNLP), 2021
​
​
Achieving model robustness through discrete adversarial training
Maor Ivgi, Jonathan Berant
Empirical Methods in Natural Language Processing (EMNLP), 2021
​
​
What's in your head? emergent behaviour in multi-task transformer models
Mor Geva, Uri Katz, Aviv Ben-Arie, Jonathan Berant
Empirical Methods in Natural Language Processing (EMNLP), 2021
​
​
COVR: a test-bed for visually grounded compositional generalization with real images
Ben Bogin, Shivanshu Gupta, Matt Gardner, Jonathan Berant
Empirical Methods in Natural Language Processing (EMNLP), 2021
​
​
​
ICCV 21 Publication:
​
Explaining in Style: Training a GAN to explain a classifier in StyleSpace
Oran Lang, Yossi Gandelsman, Michal Yarom, Yoav Wald, Gal Elidan, Avinatan Hassidim, William T. Freeman, Phillip Isola,
Amir Globerson, Michal Irani, Inbar Mosseri
International Conference on Computer Vision (ICCV), 2021
​
Neurips 21 Publications:
​
​
Differentially Private Multi-Armed Bandits in the Shuffle Model
Jay Tenenbaum, Haim Kaplan, Yishay Mansour, Uri Stemmer
Conference on Neural Information Processing Systems (Neurips), 2021
​
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
accepted to NeurIPS in spotlight category (top 3%)
Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
Conference on Neural Information Processing Systems (Neurips), 2021
​
​
Dueling Bandits with Team Comparisons
Lee Cohen, Ulrike Schmidt-Kraepelin, Yishay Mansour
Conference on Neural Information Processing Systems (Neurips), 2021
​
​
Optimal Rates for Random Order Online Optimization
Uri Sherman, Tomer Koren, Yishay Mansour
Conference on Neural Information Processing Systems (Neurips), 2021
Oralcategory (top 1%)
​
​
Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure
Aviv Rosenberg, Yishay Mansour
Conference on Neural Information Processing Systems (Neurips), 2021
​
​
A New Theoretical Framework for Fast and Accurate Online Decision-Making
Nicolò Cesa-Bianchi, Tommaso Cesari, Yishay Mansour, Vianney Perchet
Conference on Neural Information Processing Systems (Neurips), 2021
​
​
Minimax Regret for Stochastic Shortest Path
Alon Cohen, Yonathan Efroni, Yishay Mansour, Aviv Rosenberg
Conference on Neural Information Processing Systems (Neurips), 2021
​
​
A Theoretical Analysis of Fine-tuning with Linear Teachers
Gal Shachaf, Alon Brutzkus, Amir Globerson
Conference on Neural Information Processing Systems (Neurips), 2021
​
​
Continuous vs. Discrete Optimization of Deep Neural Networks
Omer Elkabetz, Nadav Cohen
accepted to NeurIPS in spotlight category (top 3%)
Conference on Neural Information Processing Systems (Neurips), 2021
​
Best-of-All-Worlds Bounds for Online Learning with Feedback Graphs
Liad Erez, Tomer Koren
Conference on Neural Information Processing Systems (Neurips), 2021
​
​
Never Go Full Batch (in Stochastic Convex Optimization)
Idan Amir, Yair Carmon, Tomer Koren, Roi Livni.
Conference on Neural Information Processing Systems (Neurips), 2021
​
Asynchronous Stochastic Optimization Robust to Arbitrary Delays
Alon Cohen, Amit Daniely, Yoel Drori, Tomer Koren, Mariano Schain
Conference on Neural Information Processing Systems (Neurips), 2021
Algorithmic Instabilities of Accelerated Gradient Descent
Amit Attia, Tomer Koren
Conference on Neural Information Processing Systems (Neurips), 2021
​
​
​
ACL-IJCNLP 21 Publications
​
Few-Shot question answering by pretraining span selection
Ori Ram, Yuval Kirstain, Jonathan Berant, Amir Globerson, Omer Levy
Association for Computational Linguistics (ACL), 2021
​
​
Span-based semantic parsing for compositional generalization
Jonathan Herzig, Jonathan Berant
Association for Computational Linguistics (ACL), 2021
​
​
Coreference Resolution without Span Representations
Yuval Kirstain, Ori Ram, Omer Levy
Association for Computational Linguistics (ACL), 2021
​
​
​
​
COLT 21 Publications
​
The Sparse Vector Technique, Revisited
Haim Kaplan, Yishay Mansour, Uri Stemmer
The 34th Annual Conference on Learning Theory (COLT 2021)
​
​
Online Markov Decision Processes with Aggregate Bandit Feedback
Alon Cohen, Haim Kaplan, Tomer Koren, Yishay Mansour
The 34th Annual Conference on Learning Theory (COLT 2021)
​
SGD Generalizes Better Than GD (And Regularization Doesn’t Help)
Idan Amir, Tomer Koren, Roi Livni
The 34th Annual Conference on Learning Theory (COLT 2021)
Lazy OCO: Online Convex Optimization on a Switching Budget
Uri Sherman, Tomer Koren
The 34th Annual Conference on Learning Theory (COLT 2021)
​​
​
Thinking Inside the Ball: Near-Optimal Minimization of the Maximal Loss
Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford
The 34th Annual Conference on Learning Theory (COLT 2021)
​​
​
Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games
Steve Hanneke, Roi Livni, Shay Moran
The 34th Annual Conference on Learning Theory (COLT 2021)
​
​
​
​
ICML 21 Publications
​
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.
​​
​
Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
Tomer Koren, Tal Lancewicki, Yishay Mansour, Shahar Segal.
International Conference on Machine Learning (ICML), 2021.
​​
​
Differentially-Private Clustering of Easy Instances
Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer.
International Conference on Machine Learning (ICML), 2021.
​​
​
Dueling Convex Optimization
Aadirupa Saha, Tomer Koren, Yishay Mansour
International Conference on Machine Learning (ICML), 2021.
​​
​
Aadirupa Saha, Tomer Koren, Yishay Mansour
International Conference on Machine Learning (ICML), 2021.
​​
​
Recovering AES Keys with a Deep Cold Boot Attack
I. Zimerman, E. Nachmani , L. Wolf
International Conference on Machine Learning (ICML), 2021.
​
HyperHyperNetwork for the Design of Antenna Arrays
S. Lutati, L. Wolf
International Conference on Machine Learning (ICML), 2021.
​​
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
John Miller, Rohan Tauri, Aditi Raghunathan, Shiori Sagawa, Pang Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon and Ludwig Schmidt
International Conference on Machine Learning (ICML), 2021.
​
Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry
Hilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar.
International Conference on Machine Learning (ICML), 2021.
​
Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with sqrt{T} Regret
Asaf Cassel, Tomer Koren
International Conference on Machine Learning (ICML), 2021.
​
Implicit Regularization in Tensor Factorization
Noam Razin, Asaf Maman, Nadav Cohen
International Conference on Machine Learning (ICML),2021.
​
​
​
Publication Highlights
​
​
Amir Globerson, ELLIS Fellow, Unit Director
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
​
​
Lior Wolf, ELLIS Fellow
​
Fidelity-based Deep Adiabatic Scheduling
​E. Ovits, L. Wolf.
International Conference on Learning Representations (ICLR) 2021
​
​
The automatic recognition of ceramics from only one photo
​F. Anichini, N. Dershowitz, N. Dubbini, G. Gattiglia, B. Itkin, L. Wolf
The ArchAIDE app. Journal of Archaeological Science: Reports, 2021
​
​
Yishay Mansour, ELLIS Fellow
Designing Committees for Mitigating Biases
Michal Feldman, Yishay Mansour, Noam Nisan, Sigal Oren, Moshe Tennenholtz
The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI) 2020
​
Apprenticeship Learning via Frank-Wolfe
Tom Zahavy, Alon Cohen, Haim Kaplan, Yishay Mansour
The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI) 2020
​
​
Jonathan Berant, ELLIS Scholar
​
​
Evaluating the evaluation of diversity in natural language generation
Guy Tevet, Jonathan Berant
European Association for Computational Linguistics (EACL) 2021
​
​
Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies
Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, Jonathan Berant.
Transactions of the Association for Computational Linguistics (TACL) 2021
​
​
Nadav Cohen, ELLIS Scholar
​
Implicit Regularization in Deep Learning May Not Be Explainable by Norms
Noam Razin and Nadav Cohen
Conference on Neural Information Processing Systems (NeurIPS) 2020
​
​
Implicit Regularization in Deep Matrix Factorization
Sanjeev Arora, Nadav Cohen, Wei Hu and Yuping Luo
Conference on Neural Information Processing Systems (NeurIPS) 2019, Spotlight Track (top 3%)
​
​
Tomer Koren, ELLIS Scholar
​
Asaf Cassel, Tomer Koren
Advanced in Neural Information Processing Systems (NeurIPS) 2020
​
​
Stochastic Optimization with Laggard Data Pipelines
Naman Agarwal, Rohan Anil, Tomer Koren, Kunal Talwar, Cyril Zhang
Advanced in Neural Information Processing Systems (NeurIPS) 2020
​
​
Tova Milo. ELLIS Fellow
​
Tova Milo
Journal of Data and Information Quality ACM J. Data Inf. Qual. (2020)​
​
Towards Autonomous, Hands-Free Data Exploration
Ori Bar El, Tova Milo, Amit Somech
10th Annual Conference on Innovative Data Systems Research (CIDR ‘20)
​
Omer Levy, ELLIS Scholar
​
Roberta: A robustly optimized bert pretraining approach
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov
2019
​
Improving distributional similarity with lessons learned from word embeddings
O Levy, Y Goldberg, I Dagan
Transactions of the Association for Computational Linguistics 2015
​
​
​
Dan Halperin, ELLIS Member
​
dRRT*: Scalable and informed asymptotically-optimal multi-robot motion planning
Rahul Shome, Kiril Solovey, Andrew Dobson, Dan Halperin, Kostas E. Bekris
Autonomous Robots (2020)
​
Refined Analysis of Asymptotically-Optimal Kinodynamic Planning in the State-Cost Space
Michal Kleinbort, Edgar Granados, Kiril Solovey, Riccardo Bonalli, Kostas E. Bekris, Dan Halperin
International Conference on Robotics and Automation (ICRA) 2020
​
​
​