| 09/07/2018, R.Pasupathy | Acceleration of Stochastic Approximation by Averaging, SIAM J. on Optimization, 30(4), 1992 |
| 09/14/2018, H. Honnappa | Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains, arXiv 1707.06386v2, 2018 |
| 09/21/2018, P. Jaiswal | Robust Stochastic Approximation Approach to Stochastic Programming, SIAM J. on Optimization, 19(4), 2009 |
| 09/28/2018, David Newton | ADAM: A Method for Stochastic Optimization, ICLR 2015, arXiv 1412.6980v9 |
| 10/05/2018, Chih-Hua Wang | Stochastic approximation for speeding up LSTD (and LSPI), arXiv 1306.2557v5 |
| 10/12/2018, Ying Sun | The Statistical Performance of Collaborative Inference, JMLR 17 (2016), 1--29 |
| 10/19/2018, Daniel Vasquez | Communication-Efficient Algorithms for Statistical Optimization, JMLR 14 (2013), 3321--3363 |
| 10/26/2018, Loris Cannelli | Distributed Stochastic Gradient Tracking Methods, Shi Pu and Angelia Nedic, arXiv 1805.11454 |
| 11/02/2018, Vinayak Rao | Train faster, generalize better: Stability of stochastic gradient descent, Moritz Hardt, Benjamin Recht, and Yoram Singer, https://arxiv.org/abs/1509.01240 |
| 11/09/2018, Raghu Pasupathy | A Newton-Rafson version of the multivariate Robbins-Monro procedure, Annals of Statistics, 13(1), 236--245 (1985) |