Kernel Ridge Regression Using Importance Sampling with Application to Seismic Response Prediction

Scalable kernel methods, including kernel ridge regression, often rely on low-rank matrix approximations using the Nystrom method, which involves selecting landmark points from large data sets. The existing approaches to selecting landmarks are typically computationally demanding as they require manipulating and performing computations with large matrices in the input or feature space. In this paper, our contribution is twofold. The first contribution is to propose a novel landmark selection method that promotes diversity using an efficient two-step approach. Our landmark selection technique follows a coarse to fine strategy, where the first step computes importance scores with a single pass over the whole data. The second step performs K-means clustering on the constructed coreset to use the obtained centroids as landmarks. Hence, the introduced method provides tunable trade-offs between accuracy and efficiency. Our second contribution is to investigate the performance of several landmark selection techniques using a novel application of kernel methods for predicting structural responses due to earthquake load and material uncertainties. Our experiments exhibit the merits of our proposed landmark selection scheme against baselines.

[1]  James T. Kwok,et al.  Clustered Nyström Method for Large Scale Manifold Learning and Dimension Reduction , 2010, IEEE Transactions on Neural Networks.

[2]  Dan Feldman,et al.  Core‐sets: An updated survey , 2019, WIREs Data Mining Knowl. Discov..

[3]  Ameet Talwalkar,et al.  On the Impact of Kernel Approximation on Learning Accuracy , 2010, AISTATS.

[4]  Georgios Alexandros Skrimpas,et al.  Employment of Kernel Methods on Wind Turbine Power Performance Assessment , 2015, IEEE Transactions on Sustainable Energy.

[5]  Daniele Calandriello,et al.  On Fast Leverage Score Sampling and Optimal Learning , 2018, NeurIPS.

[6]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[7]  Yang Wang,et al.  Applications of Support Vector Machine (SVM) Learning in Cancer Genomics. , 2018, Cancer genomics & proteomics.

[8]  Matthias W. Seeger,et al.  Using the Nyström Method to Speed Up Kernel Machines , 2000, NIPS.

[9]  Suvrit Sra,et al.  Fast DPP Sampling for Nystrom with Application to Kernel Methods , 2016, ICML.

[10]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[11]  Ameet Talwalkar,et al.  Sampling Methods for the Nyström Method , 2012, J. Mach. Learn. Res..

[12]  Mohammad Amin Hariri-Ardebili,et al.  Seismic Stability Assessment of a High-Rise Concrete Tower Utilizing Endurance Time Analysis , 2014 .

[13]  Michael W. Mahoney,et al.  Revisiting the Nystrom Method for Improved Large-scale Machine Learning , 2013, J. Mach. Learn. Res..

[14]  Alexander Gammerman,et al.  Ridge Regression Learning Algorithm in Dual Variables , 1998, ICML.

[15]  Shiliang Sun,et al.  A review of Nyström methods for large-scale machine learning , 2015, Inf. Fusion.

[16]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[17]  Stephen Becker,et al.  Randomized Clustered Nystrom for Large-Scale Kernel Machines , 2016, AAAI.

[18]  Matjaz Dolsek,et al.  Incremental dynamic analysis with consideration of modeling uncertainties , 2009 .

[19]  Andreas Krause,et al.  Training Gaussian Mixture Models at Scale via Coresets , 2017, J. Mach. Learn. Res..

[20]  Inderjit S. Dhillon,et al.  Memory Efficient Kernel Approximation , 2014, ICML.

[21]  Victor E. Saouma,et al.  Collapse Fragility Curves for Concrete Dams: Comprehensive Study , 2016 .

[22]  David P. Woodruff,et al.  Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel k-means Clustering , 2019, ICML.

[23]  Zhuang Wang,et al.  Scaling Up Kernel SVM on Limited Resources: A Low-Rank Linearization Approach , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[24]  Michael Rabadi,et al.  Kernel Methods for Machine Learning , 2015 .

[25]  Volkan Cevher,et al.  Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data , 2017, NIPS.

[26]  Silvio Lattanzi,et al.  One-Shot Coresets: The Case of k-Clustering , 2017, AISTATS.

[27]  Shusen Wang,et al.  Scalable Kernel K-Means Clustering with Nystrom Approximation: Relative-Error Bounds , 2017, J. Mach. Learn. Res..

[28]  M. A. Hariri-Ardebili,et al.  Efficient seismic reliability analysis of large-scale coupled systems including epistemic and aleatory uncertainties , 2019, Soil Dynamics and Earthquake Engineering.

[29]  Stephen Becker,et al.  Improved Fixed-Rank Nyström Approximation via QR Decomposition: Practical and Theoretical Aspects , 2017, Neurocomputing.

[30]  Sami Sieranoja,et al.  How much can k-means be improved by using better initialization and repeats? , 2019, Pattern Recognit..

[31]  Michael W. Mahoney,et al.  Fast Randomized Kernel Ridge Regression with Statistical Guarantees , 2015, NIPS.