SIAM Journal on Optimization

By C. Audet, Heinz H. Bauschke, Lorenz T. Biegler, Patrick L. Combettes, W. Cook, Felipe Cucker, Etienne de Klerk, Darinka Dentcheva †, A. Dontchev, F. Eisenbrand and 31 more. 2012

143 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Optimization & Training, Mathematical Optimization

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Stephen P. Boyd
2. Simon Shaolei Du
3. Shusen Wang
4. Jaehyun Park
5. Michael I. Jordan
6. Karl Kunisch
7. Xiang Li
8. Lili Su

In Optimization & Training

1. Michael I. Jordan
2. Qihang Lin
3. Shusen Wang
4. Zhihua Zhang
5. Tianbao Yang
6. Jakub Konecný
7. Xiang Li
8. Simon Shaolei Du

In Mathematical Optimization

1. Michael I. Jordan
2. Weijie Su
3. Simon Shaolei Du
4. Tuomas Sandholm
5. Shusen Wang
6. Mert Gurbuzbalaban
7. Stephen P. Boyd
8. Zhe Li

Citations in the corpus

• On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimization (2017, neutral): “, 2009]) and nonconvex (see [Ghadimi and Lan, 2013]) problems.”
• Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances (2019, background): “[LRP16] Laurent Lessard, Benjamin Recht, and Andrew Packard.”
• Libratus: The Superhuman AI for No-Limit Poker (2017, methodology): “Recent work suggests that subgame solving could be even faster by leveraging warm starting [Brown and Sandholm, 2016b], new pruning techniques [Brown and Sandholm, 2017a], or first-order methods [Nesterov, 2005; Kroer et al., 2017].”
• Do Subsampled Newton Methods Work for High-Dimensional Data? (2019, methodology): “[Byrd et al., 2011] Richard H Byrd, Gillian M Chin, Will Neveitt, and Jorge Nocedal.”
• Securing Distributed Machine Learning in High Dimensions (2018, background): “convex, the mean squared error of SGD is only O(1/t) with t iterations [NJLS09].”
• A semidefinite programming method for integer convex quadratic minimization (2015, methodology): “, in all problem instances, the SDP based lower bound was higher than the lower bound shown by [BHS15].”
• Algorithms for PDE‐constrained optimization (2010, methodology): “Thus, a so-called semi-smooth Newton method can be applied and it is well posed, not only in a discretized setting but also in function space, see [Hintermüller et al.(2002)Hintermüller, Ito, and Kunisch, Ulbrich(2003)].”
• A Unified Analysis of Stochastic Momentum Methods for Deep Learning (2018, methodology): “(i) The assumption on the magnitude of the gradient and the variance of stochastic gradient can be simply replaced by the magnitude of the stochastic gradient, which are standard assumptions in the previous analysis of stochastic gradient method [Ghadimi and Lan, 2013].”
• Understanding the acceleration phenomenon via high-resolution differential equations (2018, background): “[DFR18] Dmitriy Drusvyatskiy, Maryam Fazel, and Scott Roy.”