I am a Research Staff Member at IBM Research Almaden. Before joining IBM Research, I graduated with a Ph.D from University of Wisconsin-Madison in May 2013. Earlier, I finished my M.S. from Purdue University and B.Tech in Computer Sciences from Indian Institute of Technology (IIT-Delhi). My research interests are in data management, distributed machine learning, cloud object storage and resource scheduling, containers, memory and cache management, file systems and flash storage.
I work on projects focusing on high-speed data ingestion pipelines, distributed machine learning, memory caching for iterative data analytics in Apache Spark, and fast data recovery in HDFS.
- Neutrino: Revisiting Memory Caching for Iterative Data Analytics
Erci Xu, Mohit Saxena, and Lawrence Chiu
In Proceedings of Usenix HotStorage (co-located with Usenix ATC), June 2016, HotStorage
- vDrive: An Efficient and Consistent Virtual I/O System
Mohit Saxena, Pin Zhou and David A. Pease
In Proceedings of ACM TRIOS (co-located with SOSP), October 2015, TRIOS
- A Tale of Two Erasure Codes in HDFS
Mingyuan Xia, Mohit Saxena, Mario Blaum and David A. Pease
In Proceedings of 13th Usenix Conference on File and Storage Technologies, February 2015, FAST
My UW-Madison webpage with more detailed information is located here.