About

Hello! I'm a second year Computer Science Ph.D. student at Stanford University advised by Christopher Ré . My research focuses on systems in machine learning. I am currently working on a project to improve the stability of embedding algorithms, a key building block of machine learning pipelines. Previously, I also worked on a project to improve the efficiency of training ML algorithms through low-precision arithmetic. I graduated with a BS in Electrical & Computer Engineering and a BS in Computer Science from Cornell University. At Cornell, I had the opportunity to do research in computer architecture with Christopher Batten.

Projects

  • Embedding Stability. Embeddings must be continually re-trained on constantly changing data (i.e. changing word meanings, new vocabulary for word embeddings). However, training embeddings is inherently unstable, such that little to no change in data can cause dramatically different results, making debugging, repeatability, and model dependencies increasingly challenging. We study the tradeoffs of standard ML techniques to reduce this instability without compromising quality and performance. I'm presenting preliminary results on this work at the Women in Machine Learning Workshop co-located with NeurIPS in Montreal (Dec. 2018).

Past Projects

  • High-Accuracy Low-Precision Training (HALP). In collaboration with Chris De Sa and others, I worked on HALP, a gradient descent variant which is able to theoretically converge to highly accurate solutions while using low-precision fixed-point arithmetic. We empirically verified HALP on linear regression and logistic regression problems, as well as LSTMs and CNNs.[blog] [pdf] [slides]

  • Proxy Kernel for RISC-V Processor. In Christopher Batten's research group, I extended a RISC-V pipelined processor to support system calls via a proxy kernel. The work was done in PyMTL (Python-based hardware modeling framework) and C.

  • Neural Network Accelerator. As a final project for ECE 5745 Complex Digital ASIC Design, I built an accelerator to classify handwritten digits. The design was pushed through the ASIC flow using Synopsys and evaluated on power, performance, and area.

Publications and Pre-prints

  • C. De Sa, M. Leszczynski, J. Zhang, A. Marzoev, C. R. Aberger, K. Olukotun, and C. Ré. High-Accuracy Low-Precision Training. arXiv Preprint. Mar. 2018.

  • H. Freeman, M. Leszczynski, and G. Ratnaparkhi. iOS Controlled, Low Cost, Low Power Massage Vest Driven by PIC32. Circuit Cellar. Jan. 2018.

  • M. Leszczynski and J. Moreira. Machine Solver for Physics Word Problems. NIPS Intuitive Physics Workshop. Dec. 2016.

Teaching Experience

  • Cornell University
    • ECE 4750: Computer Architecture, Undergraduate Teaching Assistant (Fall 2016)
    • CS 1110: Introduction to Python, Consultant (Fall 2014, Spring 2015, Fall 2015, Spring 2016)