论文信息 - An Upper Bound for Aggregating Algorithm for Regression with Changing Dependencies

An Upper Bound for Aggregating Algorithm for Regression with Changing Dependencies

The paper presents a competitive prediction-style upper bound on the square loss of the Aggregating Algorithm for Regression with Changing Dependencies in the linear case. The algorithm is able to compete with a sequence of linear predictors provided the sum of squared Euclidean norms of differences of regression coefficient vectors grows at a sublinear rate.

Yuri Kalnishkan | Yuri Kalnishkan

[1] Jürgen Forster,et al. On Relative Loss Bounds in Generalized Linear Regression , 1999, FCT.

[2] Vladimir Vovk,et al. Aggregating strategies , 1990, COLT '90.

[3] Charles R. Johnson,et al. Topics in Matrix Analysis , 1991 .

[4] Vladimir Vovk,et al. A game of prediction with expert advice , 1995, COLT '95.

[5] Mark Herbster,et al. Tracking the Best Linear Predictor , 2001, J. Mach. Learn. Res..

[6] V. Vovk. Competitive On‐line Statistics , 2001 .

[7] Wouter M. Koolen,et al. A Closer Look at Adaptive Regret , 2012, J. Mach. Learn. Res..

[8] Yuri Kalnishkan,et al. Online Regression Competitive with Changing Predictors , 2007, ALT.

[9] Charles R. Johnson,et al. Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[10] Yuri Kalnishkan,et al. Weighted Kernel Regression for Predicting Changing Dependencies , 2007, ECML.

[11] Koby Crammer,et al. Second-order non-stationary online learning for regression , 2013, J. Mach. Learn. Res..

[12] Manfred K. Warmuth,et al. Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions , 1999, Machine Learning.

[13] Davod Khojasteh Salkuyeh. Comments on "A note on a three-term recurrence for a tridiagonal matrix" , 2006, Appl. Math. Comput..

[14] Claudio Gentile,et al. A Second-Order Perceptron Algorithm , 2002, SIAM J. Comput..