Please use this identifier to cite or link to this item:
|Title:||An efficient sparse metric learning in high-dimensional space via ℓ1-penalized log-determinant regularization|
|Source:||Qi, G.-J.,Tang, J.,Zha, Z.-J.,Chua, T.-S.,Zhang, H.-J. (2009). An efficient sparse metric learning in high-dimensional space via ℓ1-penalized log-determinant regularization. Proceedings of the 26th International Conference On Machine Learning, ICML 2009 : 841-848. ScholarBank@NUS Repository.|
|Abstract:||This paper proposes an efficient sparse metric learning algorithm in high dimensional space via an ℓ1-penalized log-determinant regularization. Compare to the most existing distance metric learning algorithms, the proposed algorithm exploits the sparsity nature underlying the intrinsic high dimensional feature space. This sparsity prior of learning distance metric serves to regularize the complexity of the distance model especially in the "less example number p and high dimension d" setting. Theoretically, by analogy to the covariance estimation problem, we find the proposed distance learning algorithm has a consistent result at rate O (√(m2log d)/n) to the target distance matrix with at most m nonzeros per row. Moreover, from the implementation perspective, this ℓ1-penalized log-determinant formulation can be efficiently optimized in a block coordinate descent fashion which is much faster than the standard semi-definite programming which has been widely adopted in many other advanced distance learning algorithms. We compare this algorithm with other state-of-the-art ones on various datasets and competitive results are obtained.|
|Source Title:||Proceedings of the 26th International Conference On Machine Learning, ICML 2009|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 16, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.