Block coordinate descent algorithms for large-scale sparse multiclass classification
Rent the article at a discountRent now
* Final gross prices may vary according to local VAT.Get Access
Over the past decade, ℓ 1 regularization has emerged as a powerful way to learn classifiers with implicit feature selection. More recently, mixed-norm (e.g., ℓ 1/ℓ 2) regularization has been utilized as a way to select entire groups of features. In this paper, we propose a novel direct multiclass formulation specifically designed for large-scale and high-dimensional problems such as document classification. Based on a multiclass extension of the squared hinge loss, our formulation employs ℓ 1/ℓ 2 regularization so as to force weights corresponding to the same features to be zero across all classes, resulting in compact and fast-to-evaluate multiclass models. For optimization, we employ two globally-convergent variants of block coordinate descent, one with line search (Tseng and Yun in Math. Program. 117:387–423, 2009) and the other without (Richtárik and Takáč in Math. Program. 1–38, 2012a; Tech. Rep. arXiv:1212.0873, 2012b). We present the two variants in a unified manner and develop the core components needed to efficiently solve our formulation. The end result is a couple of block coordinate descent algorithms specifically tailored to our multiclass formulation. Experimentally, we show that block coordinate descent performs favorably compared to other solvers such as FOBOS, FISTA and SpaRSA. Furthermore, we show that our formulation obtains very compact multiclass models and outperforms ℓ 1/ℓ 2-regularized multiclass logistic regression in terms of training speed, while achieving comparable test accuracy.
- Bach, F. R., Jenatton, R., Mairal, J., Obozinski, G. (2012) Optimization with sparsity-inducing penalties. Foundations and Trends in Machine Learning 4: pp. 1-106 CrossRef
- Bakin, S. (1999). Adaptative regression and model selection in data mining problems. Ph.D. thesis, Australian National University.
- Beck, A., Teboulle, M. (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences 2: pp. 183-202 CrossRef
- Bertsekas, D. P. (1999) Nonlinear programming. Athena Scientific, Belmont
- Boser, B. E., Guyon, I. M., Vapnik, V. N. (1992) A training algorithm for optimal margin classifiers. Proceedings of conference on learning theory (COLT). pp. 144-152
- Chang, K. W., Hsieh, C. J., Lin, C. J. (2008) Coordinate descent method for large-scale l2-loss linear support vector machines. Journal of Machine Learning Research 9: pp. 1369-1398
- Combettes, P., Wajs, V. (2005) Signal recovery by proximal forward-backward splitting. Multiscale Modeling & Simulation 4: pp. 1168-1200 CrossRef
- Crammer, K., Singer, Y. (2002) On the algorithmic implementation of multiclass kernel-based vector machines. Journal of Machine Learning Research 2: pp. 265-292
- Dredze, M., Crammer, K., Pereira, F. (2008) Confidence-weighted linear classification. Proceedings of international conference on machine learning (ICML). pp. 264-271 CrossRef
- Duchi, J., Singer, Y. (2009) Boosting with structural sparsity. Proceedings of international conference on machine learning (ICML). pp. 297-304
- Duchi, J., Singer, Y. (2009) Efficient online and batch learning using forward backward splitting. Journal of Machine Learning Research 10: pp. 2899-2934
- Elisseeff, A., Weston, J. (2001) A kernel method for multi-labelled classification. Proceedings of neural information processing systems (NIPS). pp. 681-687
- Fan, R. E., & Lin, C. J. (2007). A study on threshold selection for multi-label classification. Tech. rep., National Taiwan University.
- Friedman, J., Hastie, T., Höfling, H., Tibshirani, R. (2007) Pathwise coordinate optimization. The Annals of Applied Statistics 1: pp. 302-332 CrossRef
- Friedman, J., Hastie, T., & Tibshirani, R. (2010a). A note on the group lasso and a sparse group lasso. Tech. Rep. arXiv:1001.0736.
- Friedman, J. H., Hastie, T., Tibshirani, R. (2010) Regularization paths for generalized linear models via coordinate descent. Journal of Statistical Software 33: pp. 1-22
- Fu, W. J. (1998) Penalized regressions: the bridge versus the lasso. Journal of Computational and Graphical Statistics 7: pp. 397-416
- Lee, Y., Lin, Y., Wahba, G. (2004) Multicategory support vector machines, theory, and application to the classification of microarray data and satellite radiance data. Journal of the American Statistical Association 99: pp. 67-81 CrossRef
- Mangasarian, O. (2002) A finite Newton method for classification. Optimization Methods and Software 17: pp. 913-929 CrossRef
- Meier, L., Geer, S., Bühlmann, P. (2008) The group lasso for logistic regression. Journal of the Royal Statistical Society. Series B. Statistical Methodology 70: pp. 53-71 CrossRef
- Obozinski, G., Taskar, B., Jordan, M. I. (2010) Joint covariate selection and joint subspace selection for multiple classification problems. Statistics and Computing 20: pp. 231-252 CrossRef
- Qin, Z., Scheinberg, K., & Goldfarb, D. (2010). Efficient block-coordinate descent algorithms for the group lasso. Tech. rep., Columbia University.
- Richtárik, P., & Takáč, M. (2012a). Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function. Mathematical Programming, 1–38.
- Richtárik, P., & Takáč, M. (2012b). Parallel coordinate descent methods for big data optimization. Tech. Rep. arXiv:1212.0873.
- Rifkin, R., Klautau, A. (2004) In defense of one-vs-all classification. Journal of Machine Learning Research 5: pp. 101-141
- Shalev-Shwartz, S., Singer, Y., Srebro, N., & Cotter, A. (2010). Pegasos: primal estimated sub-gradient solver for svm. Mathematical Programming, 1–28.
- Shevade, S. K., Keerthi, S. S. (2003) A simple and efficient algorithm for gene selection using sparse logistic regression. Bioinformatics 19: pp. 2246-2253 CrossRef
- Tseng, P., Yun, S. (2009) A coordinate gradient descent method for nonsmooth separable minimization. Mathematical Programming 117: pp. 387-423 CrossRef
- Weinberger, K., Dasgupta, A., Langford, J., Smola, A., Attenberg, J. (2009) Feature hashing for large scale multitask learning. Proceedings of international conference on machine learning (ICML). pp. 1113-1120
- Weston, J., Watkins, C. (1999) Support vector machines for multi-class pattern recognition. Proceedings of European symposium on artificial neural networks, computational intelligence and machine learning. pp. 219-224
- Wright, S. J. (2012) Accelerated block-coordinate relaxation for regularized optimization. SIAM Journal on Optimization 22: pp. 159-186 CrossRef
- Wright, S. J., Nowak, R. D., Figueiredo, M. A. T. (2009) Sparse reconstruction by separable approximation. Transactions on Signal Processing 57: pp. 2479-2493 CrossRef
- Yuan, M., Lin, Y. (2006) Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society, Series B 68: pp. 49-67 CrossRef
- Yuan, G. X., Chang, K. W., Hsieh, C. J., Lin, C. J. (2010) A comparison of optimization methods and software for large-scale l1-regularized linear classification. Journal of Machine Learning Research 11: pp. 3183-3234
- Yuan, G. X., Ho, C. H., Lin, C. J. (2011) An improved glmnet for l1-regularized logistic regression. Proceedings of the international conference on knowledge discovery and data mining. pp. 33-41
- Zhang, H. H., Liu, Y., Wu, Y., Zhu, J. (2006) Variable selection for multicategory svm via sup-norm regularization. Electronic Journal of Statistics 2: pp. 149-167 CrossRef
- Zhao, P., Yu, B. (2006) On model selection consistency of lasso. Journal of Machine Learning Research 7: pp. 2541-2563
- Zou, H., Hastie, T. (2005) Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society, Series B 67: pp. 301-320 CrossRef
- Block coordinate descent algorithms for large-scale sparse multiclass classification
Volume 93, Issue 1 , pp 31-52
- Cover Date
- Print ISSN
- Online ISSN
- Springer US
- Additional Links
- Multiclass classification
- Group sparsity
- Block coordinate descent
- Industry Sectors