Maxim Naumov

Maxim Naumov joined Nvidia Research in January 2015. His interests include parallel algorithms, numerical linear algebra, optimization, graphs and deep learning. In 2015-2017 he has lead the development of spectral clustering and partitioning schemes used in the nvGRAPH library. In 2013-2015 he has lead the development of the AmgX library, which provides distributed Algebraic Multigrid, Krylov and Relaxation-based schemes. Most notably, he developed methods for sparse triangular solve, incomplete LU factorization and LU re-factorization. He has also worked on the cuBLAS, cuSPARSE and cuSOLVER(RF) libraries that are part of the CUDA Toolkit. In the past, Maxim held different positions at Nvidia Corporation Emerging Applications and Platform teams, Intel Corporation Microprocessor Technology Lab and Computational Software Lab. Also, he was awarded 2008-09 Intel Foundation Ph.D. Fellowship during his graduate studies. Maxim received his Ph.D. in Computer Science (with specialization in Computational Science and Engineering) in 2009 and his B.Sc. in Computer Science and Mathematics in 2003, all from Purdue University - West Lafayette.