Efficient Data Point Pruning for One-Class SVM

One-class SVM is a popular method for one-class classification but it needs high computation cost. This paper proposes Quix as an efficient training algorithm for one-class SVM. It prunes unnecessary data points before applying the SVM solver by computing upper and lower bounds of a parameter that determines the hyper-plane. Since we can efficiently check optimality of the hyper-plane by using the bounds, it guarantees the identical classification results to the original approach. Experiments show that it is up to 6800 times faster than existing approaches without degrading optimality.

Authors

• Yasuhiro Fujiwara NTT Communication Science Laboratories
• Sekitoshi Kanai NTT Computer and Data Science Laboratories
• Junya Arai
• Yasutoshi Ida NTT Computer and Data Science Laboratories
• Naonori Ueda

Keywords

No keywords are indexed for this paper.