Refereed Publications in Conference Proceedings
S. Sabato, S. Shalev-Shwartz "Prediction by categorical features: generalization
properties and application to feature ranking", Proceedings of The Twentieth Annual Conference on Learning Theory (COLT), 2007 .
A version with all the proofs
S. Sabato and Y. Naveh, "Preprocessing expression-based constraint satisfaction problems for stochastic local search", Proceedings of CP-AI-OR, 2007. pdf
S. Sabato, E. Yom-Tov, A. Tsherniak and S. Rosset, "Analyzing system logs: A new view of what's important", Proceedings of Second Workshop on Computer Systems with Machine Learning (SysML), 2007. pdf
S. Sabato and Y. Winter, "Against partitioned readings of reciprocals", Proceedings of 15th Amsterdam Colloquium, 2005.
S. Sabato and Y. Winter, "From semantic restrictions to reciprocal meanings", Proceedings of Formal Grammar and Mathematics of Language (FG-MOL), 2005.
Other Publications
S. Sabato, E. Yom-Tov, and O. Rodeh, "Melody - Expert-Free System Analysis", Machine Learning for Systems Problems Workshop, NIPS 2007. pdf
S. Sabato,
"Melody summarizes computer system descriptions automatically", IBM Innovation Matters web magazine, September 2007.
S. Sabato, "The Interpretation of reciprocal expressions in natural language",
M.Sc. Thesis, Supervised by Yoad Winter, Technion - Israel Institute of Technology, 2006.
Patents
S. Sabato and Y. Naveh, "Reformulation of constraint satisfaction problems for stochastic search", U.S Patent request 11/137949
S. Sabato, E. Yom-Tov and A. Tsherniak, "Apparatus for and Method of Implementing System Log Message Ranking via System Behavior Analysis", U.S Patent request 11/877679
A. Tsherniak and S. Sabato, "A System and Method for Visualization of Time-Based Events", US Patent Request 12/025776
Invited Talks
S. Sabato, "Melody - Reducing warranty costs of xServers using machine learning",
IBM Academy of Technology 5th Proactive Problem Prediction, Avoidance, and
Diagnosis Conference, April 2007.
S. Sabato, "Feature Selection for Categorical Features with Many Values", IBM Haifa Machine Learning Seminar, May 2007.