Praneeth Netrapalli

I am a researcher at Microsoft Research India, Bengaluru since August 2016. Prior to this, I was a postdoctoral researcher at Microsoft Research New England in Cambridge, MA. I obtained my MS and PhD in ECE from UT Austin where I was fortunate to be advised by Sujay Sanghavi. Before coming to UT, I worked in the Quantitative Analysis group at Goldman Sachs, Bangalore. I obtained my B-Tech in Electrical Engineering from IIT Bombay. My research focuses on designing efficient and provable algorithms for machine learning problems. Google Scholar     DBLP     arXiv

News and announcements

• I will be giving a short course on optimization in machine learning at the JTG summer school 2019 at IIT Madras.

• New papers on minimax optimization and escaping saddle points with SGD on arxiv.

• Postdoc position, broadly in the areas of optimization and machine learning, open at MSR India. See here for more details. Please drop me an email if interested.

Professional service

On the program committee of NeurIPS 2019, COLT 2019, ICML 2019, AISTATS 2019. Reviewed for ICML, COLT, NIPS, STOC, SODA, IEEE TSP, IEEE TPAMI, JMLR…

Selected publications by topic

* indicates alphabetical ordering of author names. Please see here for all publications.

Nonconvex optimization

• Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent
  C. Jin, P. Netrapalli and M. I. Jordan
  COLT 2018
  
  

• How to Escape Saddle Points Efficiently
  C. Jin, R. Ge, P. Netrapalli, S. M. Kakade and M. I. Jordan
  ICML 2017
  

Streaming algorithms/stochastic approximation

• On the insufficiency of existing momentum schemes for Stochastic Optimization
  R. Kidambi, P. Netrapalli, P. Jain and S. M. Kakade
  ICLR 2018 (Oral)
  
  

• Accelerating Stochastic Gradient Descent [*]
  P. Jain, S. M. Kakade, R. Kidambi, P. Netrapalli and A. Sidford
  COLT 2018
  
  

• Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging [*]
  P. Jain, S. M. Kakade, R. Kidambi, P. Netrapalli and A. Sidford
  Accepted for publication in JMLR
  
  

• Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm [*]
  P. Jain, C. Jin, S. M. Kakade, P. Netrapalli and A. Sidford
  COLT 2016
  

Alternating minimization

• Non-convex Robust PCA
  P. Netrapalli, U. N. Niranjan, S. Sanghavi, A. Anandkumar and P. Jain
  NIPS 2014
  
  

• Learning Sparsely Used Overcomplete Dictionaries [*]
  A. Agarwal, A. Anandkumar, P. Jain, P. Netrapalli and R. Tandon
  COLT 2014
  
  

• Phase Retrieval using Alternating Minimization
  P. Netrapalli, P. Jain and S. Sanghavi
  IEEE Transactions on Signal Processing 2015, Vol. 63, Issue 18, Pages 4814–4826
  
  

• Low-rank Matrix Completion using Alternating Minimization [*]
  P. Jain, P. Netrapalli and S. Sanghavi
  STOC 2013
  

Learning of graphs

• Finding the Graph of Epidemic Cascades
  P. Netrapalli and S. Sanghavi
  SIGMETRICS/Performance 2012
  
  

• Greedy Learning of Markov Network Structure
  P. Netrapalli, S. Banerjee, S. Sanghavi and S. Shakkottai
  Allerton 2010 (Invited)
  

Mentoring

Interns (in reverse chronological order)

• Arun Sai Suggala (CMU)

• Dheeraj Nagaraj (MIT)

• Govinda M. Kamath (Stanford)

• Rahul Kidambi (Univ. of Washington)

• Chi Jin (UC Berkeley)

Research fellows (in reverse chronological order)

• Suhas Jayaram

• Raghav Somani

• Chirag Gupta (now at CMU)

• Rahul Anand Sharma (now at CMU)

• Vivek Gupta (now at University of Utah)

• Yeshwanth Cherapanamjeri (now at UC Berkeley)

Contact details

• Address: Microsoft Research, # 9, Vigyan 1st floor, Lavelle Road, Bengaluru, Karnataka 560001, India.

• E-mail: praneeth [at] microsoft [dot] com
  

• Follow @PNetrapalli