I am a fourth-year PhD student at MIT, working with Suvrit Sra and member of the Machine Learning and Learning and Intelligent Systems groups. My research focuses on mathematical analysis of machine learning techniques and non-convex optimization. I am minoring in theoretical physics (cosmology), taught by Alan Guth.

MITの大学院生で、Suvrit Sraと一緒に研究している。機械学習の数学的な分析と非凸最適化を研究している。その他にも、理論計算機科学や位相幾何学や言語学に興味がある。

我是一个麻省理工学院的研究生。博士導師是Suvrit Sra。研究的课题是人工智能的数学分析和非凸優化。我也对理论计算机科学,拓扑学和语言学感兴趣。



My research focuses on analyzing strongly Rayleigh (SR) measures as a tool to approach machine-learning problems. These measures, among which Determinantal Point Processes have already proven to be of significant interest to the ML community, encode negative dependence between items in subsets of a ground set: they endow the space with repulsive forces between similar points, enabling a careful balancing of the quality and diversity of a subset. I aim to both develop scalable learning and sampling for SR measures over large datasets, and to leverage their properties to guide machine-learning design and analysis.

Recent news

  • [Spring 2018] I am honored to be a recipient of the 2018 Google PhD Fellowship in Machine Learning
  • [Spring 2018] Joint work with Mike Gartrell (Criteo Research) is now online: Learning DPPs by Sampling Inferred Negatives
  • [Fall 2017] I presented my research on new models for optimal design at NIPS 2017 (main conference + WIML) and as a contributed talk at the DISCML workshop
  • [Fall 2017] I’m a recipient of the Criteo Faculty Research Award Program
  • [Summer 2017] I interned in Google’s Research and Machine Intelligence team with Vitaly Kuznetsov


Time series analysis

Time series analysis

Work in progress



Image courtesy of the U.S. Geological Survey

Determinantal Point Processes

Determinantal Point Processes

Elegant and tractable strongly Rayleigh measures, with direct applications to recommender systems and summarization.

Image courtesy of CERN

Strongly Rayleigh measures

Strongly Rayleigh measures

A class of probability measures over subsets of a ground set that enable negative dependence: similar items are pushed away from each other.

Image courtesy of NASA