Publications

2022

• Faster non-convex federated learning via global and local momentum (arXiv, software)
  R. Das, A. Acharya, A. Hashemi, S. Sanghavi, I. Dhillon, U. Topcu.
  To appear in Conference on Uncertainity in Artificial Intelligence (UAI) (UAI), 2022. (Spotlight)
• Robust Training in High Dimensions via Block Coordinate Geometric Median Descent (arXiv, slides, poster, software, code)
  A. Acharya, A. Hashemi, P. Jain, S. Sanghavi, I. Dhillon, U. Topcu.
  In International Conference on Artificial Intelligence and Statistics (AISTATS), March 2022.

2021

• On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Federated Learning (pdf, software)
  A. Hashemi, A. Acharya, R. Das, H. Vikalo, S. Sanghavi, I. Dhillon.
  IEEE Transactions on Parallel and Distributed Systems (IEEE TPDS) , December 2021.

2015

• Preference Completion: Large-scale Collaborative Ranking from Pairwise Comparisons (pdf, software)
  D. Park, J. Neeman, J. Zhang, S. Sanghavi, I. Dhillon.
  In International Conference on Machine Learning (ICML), pp. 1907-1916, July 2015.

2013

• A Dirty Model for Multiple Sparse Regression (pdf, software)
  A. Jalali, P. Ravikumar, S. Sanghavi.
  IEEE Transactions on Information Theory 59(12), pp. 7947-7968, 2013.

2011

• On Learning Discrete Graphical Models using Group-Sparse Regularization (pdf, software)
  A. Jalali, P. Ravikumar, V. Vasuki, S. Sanghavi.
  In International Conference on Artificial Intelligence and Statistics (AISTATS), April 2011.

2010

• A Dirty Model for Multi-task Learning (pdf, software)
  A. Jalali, P. Ravikumar, S. Sanghavi, C. Ruan.
  In Neural Information Processing Systems (NIPS), December 2010.