A
Alexandre V. Evfimievski
Researcher at IBM
Publications - 37
Citations - 3390
Alexandre V. Evfimievski is an academic researcher from IBM. The author has contributed to research in topics: Table (database) & Computer science. The author has an hindex of 16, co-authored 35 publications receiving 3158 citations. Previous affiliations of Alexandre V. Evfimievski include Moscow State University & Cornell University.
Papers
More filters
Journal ArticleDOI
On optimizing operator fusion plans for large-scale machine learning in systemML
Matthias Boehm,Berthold Reinwald,Dylan Hutchison,Prithviraj Sen,Alexandre V. Evfimievski,Niketan Pansare +5 more
TL;DR: In this paper, a cost-based optimization framework for fusion plans is proposed and integrated into Apache SystemML, where candidate exploration and selection of fusion plans, as well as code generation of local and distributed operations over dense, sparse, and compressed data are presented.
Patent
Mining association rules over privacy preserving data
TL;DR: In this article, a method of mining association rules from the databases while maintaining privacy of individual transactions within the databases through randomization is proposed, which randomly drops true items from transactions within a database and randomly inserts false items into the transactions.
Proceedings Article
SPOOF: Sum-Product Optimization and Operator Fusion for Large-Scale Machine Learning.
Tarek Elgamal,Shangyu Luo,Matthias Boehm,Alexandre V. Evfimievski,Shirish Tatikonda,Berthold Reinwald,Prithviraj Sen +6 more
TL;DR: Spoof is introduced, an architecture to automatically identify algebraic simplification rewrites, and generate fused operators in a holistic framework, and a snapshot of the overall system is described, including key techniques of sum-product optimization and code generation.
Journal Article
SystemML's Optimizer: Plan Generation for Large-Scale Machine Learning Programs.
Matthias Böhm,Douglas Burdick,Alexandre V. Evfimievski,Berthold Reinwald,Frederick Reiss,Prithviraj Sen,Shirish Tatikonda,Yuanyuan Tian +7 more
TL;DR: The SystemML optimizer, its compilation chain, and selected optimization phases for generating efficient execution plans for declarative, large-scale machine learning via a high-level language with R-like syntax are described.
Patent
System and method for tracking database disclosures
TL;DR: In this article, a system and method is provided for identifying the source of an unauthorized database disclosure. But, the method only stores a plurality of past database queries and determines the relevance of the results of the past queries (query results) to a sensitive table containing the unauthorized disclosed data.