Acceleration via Symplectic Discretization of High-Resolution Differential Equations
暂无分享,去创建一个
Michael I. Jordan | Simon S. Du | Bin Shi | Weijie J. Su | S. Du | Bin Shi
[1] E. Hairer,et al. Geometric Numerical Integration: Structure Preserving Algorithms for Ordinary Differential Equations , 2004 .
[2] Alexandre M. Bayen,et al. Accelerated Mirror Descent in Continuous and Discrete Time , 2015, NIPS.
[3] J. Slack. How to make the gradient , 1994, Nature.
[4] Michael I. Jordan,et al. Understanding the acceleration phenomenon via high-resolution differential equations , 2018, Mathematical Programming.
[5] Y. Nesterov. A method for solving the convex programming problem with convergence rate O(1/k^2) , 1983 .
[6] Jelena Diakonikolas,et al. The Approximate Duality Gap Technique: A Unified Theory of First-Order Methods , 2017, SIAM J. Optim..
[7] Andre Wibisono,et al. A variational perspective on accelerated methods in optimization , 2016, Proceedings of the National Academy of Sciences.
[8] Peter L. Bartlett,et al. Acceleration and Averaging in Stochastic Descent Dynamics , 2017, NIPS.
[9] O. Nelles,et al. An Introduction to Optimization , 1996, IEEE Antennas and Propagation Magazine.
[10] Stephen P. Boyd,et al. A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights , 2014, J. Mach. Learn. Res..
[11] Michael I. Jordan,et al. A Lyapunov Analysis of Momentum Methods in Optimization , 2016, ArXiv.
[12] Yurii Nesterov,et al. Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.
[13] Sébastien Bubeck,et al. Convex Optimization: Algorithms and Complexity , 2014, Found. Trends Mach. Learn..
[14] Aryan Mokhtari,et al. Direct Runge-Kutta Discretization Achieves Acceleration , 2018, NeurIPS.
[15] Saeed Ghadimi,et al. Accelerated gradient methods for nonconvex nonlinear and stochastic programming , 2013, Math. Program..
[16] Boris Polyak. Some methods of speeding up the convergence of iteration methods , 1964 .
[17] Zeyuan Allen-Zhu,et al. How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD , 2018, NeurIPS.
[18] Michael I. Jordan,et al. On Symplectic Optimization , 2018, 1802.03653.