Learning with Non-Convex Truncated Losses by SGD
暂无分享,去创建一个
Rong Jin | Tianbao Yang | Shenghuo Zhu | Sen Yang | Chi Zhang | Yi Xu | Tianbao Yang | Yi Xu | Rong Jin | Shenghuo Zhu | Sen Yang | Chi Zhang
[1] Robert C. Williamson,et al. From Stochastic Mixability to Fast Rates , 2014, NIPS.
[2] P. J. Huber. Robust Estimation of a Location Parameter , 1964 .
[3] Nicolò Cesa-Bianchi,et al. Bandits With Heavy Tail , 2012, IEEE Transactions on Information Theory.
[4] Daniel J. Hsu,et al. Loss Minimization and Parameter Estimation with Heavy Tails , 2013, J. Mach. Learn. Res..
[5] S. Mendelson,et al. Learning subgaussian classes : Upper and minimax bounds , 2013, 1305.4825.
[6] S. Boucheron,et al. Theory of classification : a survey of some recent advances , 2005 .
[7] Le Chang,et al. Robust Lasso Regression Using Tukey's Biweight Criterion , 2018, Technometrics.
[8] Nassir Navab,et al. Robust Optimization for Deep Regression , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).
[9] Shahar Mendelson,et al. Regularization and the small-ball method II: complexity dependent error rates , 2016, J. Mach. Learn. Res..
[10] Mehryar Mohri,et al. Relative deviation learning bounds and generalization with unbounded loss functions , 2013, Annals of Mathematics and Artificial Intelligence.
[11] Tianbao Yang,et al. First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time , 2017, NeurIPS.
[12] Frederick R. Forst,et al. On robust estimation of the location parameter , 1980 .
[13] Dmitriy Drusvyatskiy,et al. Stochastic model-based minimization of weakly convex functions , 2018, SIAM J. Optim..
[14] M. Talagrand. The Generic chaining : upper and lower bounds of stochastic processes , 2005 .
[15] S. Mendelson,et al. Regularization and the small-ball method I: sparse recovery , 2016, 1601.05584.
[16] Felipe Cucker,et al. On the mathematical foundations of learning , 2001 .
[17] Saeed Ghadimi,et al. Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming , 2013, SIAM J. Optim..
[18] O. Catoni. Challenging the empirical mean and empirical variance: a deviation study , 2010, 1009.2048.
[19] V. Yohai,et al. Robust Statistics: Theory and Methods , 2006 .
[20] Po-Ling Loh,et al. High-dimensional regression with noisy and missing data: Provable guarantees with non-convexity , 2011, NIPS.
[21] Zhi-Hua Zhou,et al. 𝓁1-regression with Heavy-tailed Distributions , 2018, ArXiv.
[22] Naomi S. Altman,et al. Quantile regression , 2019, Nature Methods.
[23] Po-Ling Loh,et al. Corrupted and missing predictors: Minimax bounds for high-dimensional linear regression , 2012, 2012 IEEE International Symposium on Information Theory Proceedings.
[24] A. Montanari,et al. The landscape of empirical risk for nonconvex losses , 2016, The Annals of Statistics.
[25] S. Geer. Applications of empirical process theory , 2000 .
[26] P. Bartlett,et al. Empirical minimization , 2006 .
[27] John Darzentas,et al. Problem Complexity and Method Efficiency in Optimization , 1983 .
[28] Rong Jin,et al. Empirical Risk Minimization for Stochastic Convex Optimization: $O(1/n)$- and $O(1/n^2)$-type of Risk Bounds , 2017, COLT.
[29] Noga Alon,et al. The space complexity of approximating the frequency moments , 1996, STOC '96.
[30] P. Massart,et al. Concentration inequalities and model selection , 2007 .
[31] Yin Chen,et al. Fused sparsity and robust estimation for linear models with unknown variance , 2012, NIPS.
[32] Po-Ling Loh,et al. Statistical consistency and asymptotic normality for high-dimensional robust M-estimators , 2015, ArXiv.
[33] P. Cochat,et al. Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.
[34] S. Mendelson. Learning without concentration for general loss functions , 2014, 1410.3192.
[35] Trac D. Tran,et al. Robust Lasso With Missing and Grossly Corrupted Observations , 2011, IEEE Transactions on Information Theory.
[36] Furong Huang,et al. Escaping From Saddle Points - Online Stochastic Gradient for Tensor Decomposition , 2015, COLT.
[37] Binh T. Nguyen,et al. Fast learning rates with heavy-tailed losses , 2016, NIPS.
[38] V. Koltchinskii,et al. Oracle inequalities in empirical risk minimization and sparse recovery problems , 2011 .
[39] Peter Grünwald,et al. Fast Rates for General Unbounded Loss Functions: From ERM to Generalized Bayes , 2016, J. Mach. Learn. Res..
[40] R. Gnanadesikan,et al. Probability plotting methods for the analysis for the analysis of data , 1968 .
[41] Daniel J. Hsu,et al. Heavy-tailed regression with a generalized median-of-means , 2014, ICML.
[42] Michael J. Black,et al. The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields , 1996, Comput. Vis. Image Underst..
[43] Trac D. Tran,et al. Exact Recoverability From Dense Corrupted Observations via $\ell _{1}$-Minimization , 2011, IEEE Transactions on Information Theory.
[44] Jean-Yves Audibert,et al. Robust linear least squares regression , 2010, 1010.0074.
[45] Prateek Jain,et al. Consistent Robust Regression , 2017, NIPS.
[46] Prateek Jain,et al. Robust Regression via Hard Thresholding , 2015, NIPS.
[47] Shahar Mendelson,et al. Learning without Concentration , 2014, COLT.
[48] G. Lugosi,et al. Empirical risk minimization for heavy-tailed losses , 2014, 1406.2462.
[49] Lorenzo Rosasco,et al. Are Loss Functions All the Same? , 2004, Neural Computation.
[50] Shahar Mendelson,et al. General nonexact oracle inequalities for classes with a subexponential envelope , 2012, 1206.0871.
[51] Yuchen Zhang,et al. A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics , 2017, COLT.
[52] Joachim M. Buhmann,et al. Fast and Robust Least Squares Estimation in Corrupted Linear Models , 2014, NIPS.
[53] Léon Bottou,et al. Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.
[54] Dmitriy Drusvyatskiy,et al. Stochastic subgradient method converges at the rate O(k-1/4) on weakly convex functions , 2018, ArXiv.
[55] Karthik Sridharan,et al. Learning with Square Loss: Localization through Offset Rademacher Complexity , 2015, COLT.
[56] Dmitriy Drusvyatskiy,et al. Stochastic Subgradient Method Converges on Tame Functions , 2018, Foundations of Computational Mathematics.