1. [1] L. Berrada, A. Zisserman, and M.P. Kumar, “Smooth loss functions for deep top-k classification,” 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30-May 3, 2018, Conference Track Proceedings, 2018.
2. [2] D.P. Bertsekas, Nonlinear Programming, Athena Scientific, 1999.
3. [3] X. Chang, Y.-L. Yu, and Y. Yang, “Robust top-k multiclass SVM for visual category recognition,” Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining-KDD 17, ACM Press, pp.75-83, 2017. 10.1145/3097983.3097991
4. [4] D. Chu, R. Lu, J. Li, X. Yu, C. Zhang, and Q. Tao, “Optimizing top-k multiclass SVM via semismooth newton algorithm,” IEEE Transactions on Neural Networks and Learning Systems, vol.29, no.12, pp.6264-6275, Dec. 2018. 10.1109/tnnls.2018.2826039
5. [5] K. Crammer and Y. Singer, “On the algorithmic implementation of multiclass kernel-based vector machines,” J. Mach. Learn. Res., vol.2, pp.265-292, March 2002.