Deep Learning

• 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.
• Learning long term dependencies via Fourier recurrent units (pdf, arXiv, software)
  J. Zhang, Y. Lin, Z. Song, I. Dhillon.
  In International Conference on Machine Learning (ICML), pp. 5810–5818, July 2018.
• Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization (pdf, arXiv, software)
  J. Zhang, Q. Lei, I. Dhillon.
  In International Conference on Machine Learning (ICML), pp. 5801–5809, July 2018.
• Recovery Guarantees for One-hidden-layer Neural Networks (pdf, arXiv, software)
  K. Zhong, Z. Song, P. Jain, P. Bartlett, I. Dhillon.
  In International Conference on Machine Learning (ICML), pp. 4140-4149, August 2017. (Oral)