Megan Leszczynski - Stanford University

I'm a Computer Science Ph.D. student at Stanford University advised by Christopher Ré. My research interests lie at the intersection of machine learning and systems. Recently, I have been excited about learning embeddings of data, including words, source code, and knowledge graph entities. 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. I am supported by the National Science Foundation Graduate Research Fellowship and the Stanford EDGE Fellowship.


Selected Projects

  • Bootleg, a self-supervised named entity disambiguation (NED) system for the tail. Bootleg improves over 50 F1 points over a BERT NED baseline on disambiguating tail (i.e rarely seen) entities in Wikipedia, while achieving state-of-the-art performance on standard, sentence-level NED benchmarks. [website] [code]

  • Embedding Stability, a study of the impact of word embedding memory on the downstream instability of NLP tasks. Embeddings must be continually re-trained on constantly changing data. However, training is inherently unstable, such that small changes in data can cause dramatically different results. We explore measures to estimate when this instability will impact downstream NLP tasks. [pdf] [slides]

  • High-Accuracy Low-Precision Training (HALP), a gradient descent variant which is able to theoretically converge to highly accurate solutions while using low-precision. We empirically verified HALP on linear regression and logistic regression problems, as well as LSTMs and CNNs. [blog] [pdf] [slides]

Publications and Preprints

Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation
Laurel Orr*, Megan Leszczynski*, Neel Guha, Sen Wu, Simran Arora, Xiao Ling, Christopher Ré
In CIDR, 2021.

Megan Leszczynski, Avner May, Jian Zhang, Sen Wu, Christopher Richard Aberger, Christopher Ré
In MLSys, 2020.

Tri Dao, Nimit Sohoni, Albert Gu, Matthew Eichhorn, Amit Blonder, Megan Leszczynski, Atri Rudra, Christopher Ré
In ICLR, 2020. Spotlight.

Nimit Sharad Sohoni, Christopher Richard Aberger, Megan Leszczynski, Jian Zhang, Christopher Ré
arXiv Preprint, 2019.

Quantifying the Stability of Word Embeddings
Megan Leszczynski, Sen Wu, Christopher Richard Aberger, Christopher Ré
In WiML at NeurIPS, 2018.

Christopher De Sa, Megan Leszczynski, Jian Zhang, Alana Marzoev, Christopher Richard Aberger, Kunle Olukotun, Christopher Ré
arXiv Preprint, 2018.

iOS Controlled, Low Cost, Low Power Massage Vest Driven by PIC32
Harry Freeman, Megan Leszczynski, Gargi Ratnaparkhi
Circuit Cellar, 2018.

Megan Leszczynski and José Moreira
In NeurIPS Intuitive Physics Workshop, 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)