F. Bach and Z. Harchaoui. DIFFRAC : a discriminative and flexible framework for clustering. We present a novel linear clustering framework (DIFFRAC) which relies on a lin- ear discriminative cost function and a convex relaxation of a combinatorial op- timization problem. The large convex optimization problem is solved through a sequence of lower dimensional singular value decompositions. This framework has several attractive properties: (1) although apparently similar to K-means, it exhibits superior clustering performance than K-means, in particular in terms of robustness to noise. (2) It can be readily extended to non linear clustering if the discriminative cost function is based on positive definite kernels, and can then be seen as an alternative to spectral clustering. (3) Prior information on the partition is easily incorporated, leading to state-of-the-art performance for semi-supervised learning, for clustering or classification. We present empirical evaluations of our algorithms on synthetic and real medium-scale datasets
Keywords for this software
References in zbMATH (referenced in 4 articles )
Showing results 1 to 4 of 4.
- Flammarion, Nicolas; Palaniappan, Balamurugan; Bach, Francis: Robust discriminative clustering with sparse regularizers (2017)
- Sugiyama, Masashi; Niu, Gang; Yamada, Makoto; Kimura, Manabu; Hachiya, Hirotaka: Information-maximization clustering based on squared-loss mutual information (2014)
- Sugiyama, Masashi: Machine learning with squared-loss mutual information (2013)
- Kokiopoulou, E.; Chen, Jie; Saad, Yousef: Trace optimization and eigenproblems in dimension reduction methods. (2011)