I'm a PhD student in the Computer Science Department at Princeton University, working under the advisement of Sanjeev Arora. Previously I received my B.S.E. degree at Princeton University as well. I work in the intersection of machine learning and theoretical computer science, with the primary goal of designing provable and practical algorithms for problems arising in machine learning. |

- Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods. With Yuanzhi Li.
*NIPS 2016* - Tight algorithms and lower bounds for approximately convex optimization. With Yuanzhi Li.
*NIPS 2016* - Non-negative matrix factorization using a decode-and-update approach. With Yuanzhi Li and Yingyu Liang.
*NIPS 2016* - Recovery guarantee of weighted low-rank approximation via alternating minimization. With Yuanzhi Li and Yingyu Liang.
*ICML 2016* - How to calculate partition functions using convex programming hierarchies: provable bounds for variational methods.
*COLT 2016* - On some provably correct cases of variational inference for topic models. With Pranjal Awasthi.
*NIPS 2015, Spotlight*

- Linear algebraic structure of word senses, with applications to polysemy. With Sanjeev Arora, Yuanzhi Li, Yingyu Liang and Tengyu Ma.
*Manuscript* - RAND-WALK: a latent variable model approach to word embeddings. With Sanjeev Arora, Yuanzhi Li, Yingyu Liang and Tengyu Ma.
*Accepted to Transactions of the Association for Computational Linguistics (TACL)*

- Label optimal regret bounds for online local learning. With Pranjal Awasthi, Moses Charikar and Kevin A. Lai.
*COLT 2015*

- On routing disjoint paths in bounded treewidth graphs. With Alina Ene, Matthias Mnich and Marcin Pilipczuk.
*To appear in SWAT 2016* - Skeletal rigidity of phylogenetic trees. With Howard Cheng, Satyan Devadoss, Brian Li.
*Discrete Applied Mathematics 170, 2014.* - What makes a tree a straight skeleton? With Oswin Aichholzer, Howard Cheng, Thomas Hackl, Stefan Huber, Brian Li.
*Canadian Conference on Computational Geometry 2012.*

- How to calculate partition functions using convex programming hierarchies: provable bounds for variational methods
- COLT (New York City, 2016) [Video]
- On some provably correct cases of variational inference for topic models
- NIPS (Montreal, 2015) [Video, talk starts circa 11:45]
- Random walks on context spaces: towards an explanation of the mysteries of semantic word embeddings
- China Theory Week (Jiao Tong University, Shanghai, 2015)
- Label optimal regret bounds for online local learning
- COLT (Paris, 2015) [Video]

- Grader for COS433 (Cryptography) at Princeton: Fall 2011/12
- Teaching assistant for COS451 (Computational Geometry) at Princeton: Fall 2013/14
- Teaching assistant for COS445 (Networks, Economics and Computing) at Princeton: Spring 2014

- The easiest way to reach me is email. My address is lastname
*at*princeton.edu