Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Raman Arora

Machine Unlearning via Algorithmic Stability


Feb 25, 2021
Enayat Ullah, Tung Mai, Anup Rao, Ryan Rossi, Raman Arora


  Access Paper or Ask Questions

On Convergence and Generalization of Dropout Training


Oct 23, 2020
Poorya Mianjy, Raman Arora

* In Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2020 

  Access Paper or Ask Questions

Adversarial Robustness of Supervised Sparse Coding


Oct 22, 2020
Jeremias Sulam, Ramchandran Muthumukar, Raman Arora

* Advances in Neural Information Processing Systems, 2020 

  Access Paper or Ask Questions

FetchSGD: Communication-Efficient Federated Learning with Sketching


Jul 15, 2020
Daniel Rothchild, Ashwinee Panda, Enayat Ullah, Nikita Ivkin, Ion Stoica, Vladimir Braverman, Joseph Gonzalez, Raman Arora


  Access Paper or Ask Questions

Corralling Stochastic Bandit Algorithms


Jun 28, 2020
Raman Arora, Teodor V. Marinov, Mehryar Mohri


  Access Paper or Ask Questions

Is Network the Bottleneck of Distributed Training?


Jun 24, 2020
Zhen Zhang, Chaokun Chang, Haibin Lin, Yida Wang, Raman Arora, Xin Jin


  Access Paper or Ask Questions

Dropout: Explicit Forms and Capacity Control


Mar 06, 2020
Raman Arora, Peter Bartlett, Poorya Mianjy, Nathan Srebro


  Access Paper or Ask Questions

Private Stochastic Convex Optimization: Efficient Algorithms for Non-smooth Objectives


Feb 22, 2020
Raman Arora, Teodor V. Marinov, Enayat Ullah


  Access Paper or Ask Questions

Multiview Representation Learning for a Union of Subspaces


Dec 30, 2019
Nils Holzenberger, Raman Arora


  Access Paper or Ask Questions

Bandits with Feedback Graphs and Switching Costs


Jul 29, 2019
Raman Arora, Teodor V. Marinov, Mehryar Mohri


  Access Paper or Ask Questions

On Dropout and Nuclear Norm Regularization


May 28, 2019
Poorya Mianjy, Raman Arora

* Proceedings of the 36th International Conference on Machine Learning, PMLR 97:4575-4584, 2019 

  Access Paper or Ask Questions

Communication-efficient distributed SGD with Sketching


Mar 12, 2019
Nikita Ivkin, Daniel Rothchild, Enayat Ullah, Vladimir Braverman, Ion Stoica, Raman Arora

* 21 pages, 6 figures 

  Access Paper or Ask Questions

Learning from Multiview Correlations in Open-Domain Videos


Nov 21, 2018
Nils Holzenberger, Shruti Palaskar, Pranava Madhyastha, Florian Metze, Raman Arora


  Access Paper or Ask Questions

Policy Regret in Repeated Games


Nov 09, 2018
Raman Arora, Michael Dinitz, Teodor V. Marinov, Mehryar Mohri

* To appear at NIPS 2018; 25 pages 

  Access Paper or Ask Questions

Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features


Aug 02, 2018
Enayat Ullah, Poorya Mianjy, Teodor V. Marinov, Raman Arora

* 38 pages, 2 figures 

  Access Paper or Ask Questions

On the Implicit Bias of Dropout


Jun 26, 2018
Poorya Mianjy, Raman Arora, Rene Vidal

* 17 pages, 3 figures, In Proceedings of the Thirty-fifth International Conference on Machine Learning (ICML), 2018 

  Access Paper or Ask Questions

Visual Robot Task Planning


Mar 30, 2018
Chris Paxton, Yotam Barnoy, Kapil Katyal, Raman Arora, Gregory D. Hager

* 8 pages, IEEE format, currently in review 

  Access Paper or Ask Questions

Understanding Deep Neural Networks with Rectified Linear Units


Feb 28, 2018
Raman Arora, Amitabh Basu, Poorya Mianjy, Anirbit Mukherjee

* ICLR 2028 
* The poly(data) exact training algorithm has been improved to now be applicable to any single hidden layer R^n-> R ReLU DNN and there is a cleaner pseudocode for it given on page 8. Also now on page 7 there is a more precise description about when and how the Zonotope construction improves on the Theorem 4 of this paper, arXiv:1402.1869 

  Access Paper or Ask Questions

Stochastic Approximation for Canonical Correlation Analysis


Feb 26, 2018
Raman Arora, Teodor V. Marinov, Poorya Mianjy, Nathan Srebro


  Access Paper or Ask Questions

On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don't Worry About Its Nonsmooth Loss Function


Feb 14, 2018
Xingguo Li, Haoming Jiang, Jarvis Haupt, Raman Arora, Han Liu, Mingyi Hong, Tuo Zhao


  Access Paper or Ask Questions

Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization


Jan 20, 2018
Xingguo Li, Junwei Lu, Raman Arora, Jarvis Haupt, Han Liu, Zhaoran Wang, Tuo Zhao


  Access Paper or Ask Questions

Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction


Dec 23, 2017
Xingguo Li, Raman Arora, Han Liu, Jarvis Haupt, Tuo Zhao


  Access Paper or Ask Questions

On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization


Nov 22, 2017
Xingguo Li, Tuo Zhao, Raman Arora, Han Liu, Mingyi Hong

* Accepted by JLMR 

  Access Paper or Ask Questions

Learning to Imagine Manipulation Goals for Robot Task Planning


Nov 09, 2017
Chris Paxton, Kapil Katyal, Christian Rupprecht, Raman Arora, Gregory D. Hager


  Access Paper or Ask Questions

Deep Generalized Canonical Correlation Analysis


Jun 15, 2017
Adrian Benton, Huda Khayrallah, Biman Gujral, Dee Ann Reisinger, Sheng Zhang, Raman Arora

* 14 pages, 6 figures 

  Access Paper or Ask Questions

Disease Trajectory Maps


Jun 29, 2016
Peter Schulam, Raman Arora


  Access Paper or Ask Questions

Embedding Lexical Features via Low-Rank Tensors


Apr 02, 2016
Mo Yu, Mark Dredze, Raman Arora, Matthew Gormley

* Accepted by NAACL 2016 

  Access Paper or Ask Questions

On Deep Multi-View Representation Learning: Objectives and Optimization


Feb 02, 2016
Weiran Wang, Raman Arora, Karen Livescu, Jeff Bilmes


  Access Paper or Ask Questions