Journals Conference Proceedings Book Chapters White Papers Misc.

On-going Work #

• Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs
  Or Sharir and Anima Anandkumar.
  Appeared at the Efficient Systems for Foundation Models Workshop @ ICML 2023.

• Towards Neural Variational Monte Carlo That Scales Linearly with System Size
  Or Sharir, Garnet Chan, and Anima Anandkumar.
  Appeared at the AI4Science Workshop @ NeurIPS 2022.

Journals #

• Neural Tensor Contractions and the Expressive Power of Deep Neural Quantum States
  Or Sharir, Amnon Shashua, and Giuseppe Carleo.
  Physical Review B (PRB), 106, 205136, 2022. (arXiv version)
• Deep Autoregressive Models for the Efficient Variational Simulation of Many-body Quantum Systems
  Or Sharir, Yoav Levine, Noam Wies, Giuseppe Carleo, and Amnon Shashua.
  Physical Review Letters (PRL) 124, 020503, 2020. (arXiv version)
• Quantum Entanglement in Deep Learning Architectures
  Yoav Levine, Or Sharir, Nadav Cohen, and Amnon Shashua.
  Physical Review Letters (PRL) 122, 065301, 2019. (arXiv version)

Conference Proceedings #

• Limits to Depth Efficiencies of Self-Attention
  Yoav Levine, Noam Wies, Or Sharir, Hofit Bata, and Amnon Shashua.
  Conference on Neural Information Processing Systems (NeurIPS) 2021. (arXiv version)
• SenseBERT: Driving Some Sense into BERT
  Yoav Levine, Barak Lenz, Or Dagan, Dan Padnos, Or Sharir, Shai Shalev-Shwartz, Amnon Shashua, and Yoav Shoham.
  Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL) 2020. (arXiv version)
• Sum-Product-Quotient Networks
  Or Sharir and Amnon Shashua.
  Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics (AISTATS) 2018. (arXiv version)
• On the Expressive Power of Overlapping Architectures of Deep Learning
  Or Sharir and Amnon Shashua.
  International Conference on Learning Representations (ICLR) Conference Track 2018. (arXiv version)
• On the Expressive Power of Deep Learning: A Tensor Analysis
  Nadav Cohen, Or Sharir, and Amnon Shashua.
  Conference on Learning Theory (COLT) 2016. (arXiv version)
• Deep SimNets
  Nadav Cohen, Or Sharir, and Amnon Shashua.
  Conference on Computer Vision and Pattern Recognition (CVPR) 2016. (arXiv version)

Book Chapters #

• Bridging Many-Body Quantum Physics and Deep Learning via Tensor Networks
  Yoav Levine, Or Sharir, Nadav Cohen, Amnon Shashua.
  Mathematical Aspects of Deep Learning, Cambridge University Press. 2022.
• Tensors for Deep Learning Theory: Analyzing Deep Learning Architectures via Tensorization
  Yoav Levine, Noam Wies, Or Sharir, Nadav Cohen, Amnon Shashua.
  Tensors for Data Processing: Theory, Methods and Applications, Academic Press. 2022.

White Papers #

• Jurassic-1: Technical details and evaluation
  Opher Lieber, Or Sharir, Barak Lenz, and Yoav Shoham.
  White Paper. AI21 Labs. 2021.
• Technical Report: Auxiliary Tuning and its Application to Conditional Text Generation
  Yoel Zeldes, Dan Padnos, Or Sharir, Barak Peleg.
  White Paper. AI21 Labs. 2020.
• The Cost of Training NLP Models: A Concise Overview
  Or Sharir, Barak Peleg, and Yoav Shoham.
  White Paper. AI21 Labs. 2020.

Workshops, Invited Papers, and Preprints #

• Benefits of Depth for Long-Term Memory of Recurrent Networks
  Yoav Levine, Or Sharir, and Amnon Shashua
  International Conference on Learning Representations (ICLR) Workshop Track 2018. (arXiv version)
• Analysis and Design of Convolutional Networks via Hierarchical Tensor Decompositions
  Nadav Cohen, Or Sharir, Yoav Levine, Ronen Tamari, David Yakira and Amnon Shashua.
  Intel Collaborative Research Institute Special Issue on Deep Learning Theory. 2017.
• Tensorial Mixture Models
  Or Sharir, Ronen Tamari, Nadav Cohen, and Amnon Shashua.
  arXiv Preprint. 2016.