Open Problem: Do Good Algorithms Necessarily Query Bad Points?
暂无分享,去创建一个
[1] Prateek Jain,et al. Making the Last Iterate of SGD Information Theoretically Optimal , 2019, COLT.
[2] Maxim Raginsky,et al. Information-Based Complexity, Feedback and Dynamics in Convex Programming , 2010, IEEE Transactions on Information Theory.
[3] John Darzentas,et al. Problem Complexity and Method Efficiency in Optimization , 1983 .
[4] Boris Polyak,et al. Acceleration of stochastic approximation by averaging , 1992 .
[5] Prateek Jain,et al. Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging , 2016, ArXiv.
[6] Sham M. Kakade,et al. The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure , 2019, NeurIPS.
[7] E. L. Lehmann,et al. Theory of point estimation , 1950 .
[8] Eric Moulines,et al. Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n) , 2013, NIPS.
[9] Prateek Jain,et al. Accelerating Stochastic Gradient Descent , 2017, ArXiv.
[10] Ohad Shamir,et al. Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes , 2012, ICML.
[11] D. Ruppert,et al. Efficient Estimations from a Slowly Convergent Robbins-Monro Process , 1988 .
[12] Martin J. Wainwright,et al. Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization , 2010, IEEE Transactions on Information Theory.
[13] H. Robbins. A Stochastic Approximation Method , 1951 .
[14] Zeyuan Allen-Zhu,et al. How To Make the Gradients Small Stochastically , 2018, NIPS 2018.
[15] Nicholas J. A. Harvey,et al. Tight Analyses for Non-Smooth Stochastic Gradient Descent , 2018, COLT.