Publications

(2020). Random Reshuffling: Simple Analysis with Vast Improvements.

PDF Code Poster Slides arXiv NeurIPS

(2020). Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms.

PDF arXiv

(2019). Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates.

PDF Poster arXiv NeurIPS

(2019). Adaptive Gradient Descent without Descent.

PDF Code Slides arXiv ICML Video

(2019). Sinkhorn Algorithm as a Special Case of Stochastic Mirror Descent.

PDF Poster Slides arXiv NeurIPS

(2019). Tighter Theory for Local SGD on Identical and Heterogeneous Data.

PDF Slides arXiv AISTATS

(2019). First Analysis of Local GD on Heterogeneous Data.

PDF Slides arXiv NeurIPS

(2019). A Self-supervised Approach to Hierarchical Forecasting with Applications to Groupwise Synthetic Controls.

PDF arXiv ICML

(2019). MISO is Making a Comeback With Better Proofs and Rates.

PDF arXiv

(2019). DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate.

PDF arXiv AISTATS

(2019). Revisiting Stochastic Extragradient.

PDF arXiv AISTATS

(2019). A Stochastic Decoupling Method for Minimizing the Sum of Smooth and Non-Smooth Functions.

PDF Slides arXiv

(2019). Stochastic Distributed Learning with Gradient Quantization and Variance Reduction.

PDF arXiv

(2019). Distributed Learning with Compressed Gradient Differences.

PDF arXiv

(2019). 99% of Worker-Master Communication in Distributed Optimization Is Not Needed.

PDF arXiv UAI

(2018). A Stochastic Penalty Model for Convex and Nonconvex Optimization with Big Constraints.

PDF arXiv

(2018). SEGA: Variance Reduction via Gradient Sketching. In Advances in Neural Information Processing Systems, 2018.

PDF arXiv NIPS

(2018). A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning. International Conference on Machine Learning.

PDF pmlr

(2018). A Distributed Flexible Delay-tolerant Proximal Gradient Algorithm.

PDF arXiv SIAM