B
Balaji Krishnapuram
Researcher at Siemens
Publications - 84
Citations - 4180
Balaji Krishnapuram is an academic researcher from Siemens. The author has contributed to research in topics: Support vector machine & Feature selection. The author has an hindex of 28, co-authored 84 publications receiving 3918 citations. Previous affiliations of Balaji Krishnapuram include IBM & Duke University.
Papers
More filters
Journal ArticleDOI
Sparse multinomial logistic regression: fast algorithms and generalization bounds
TL;DR: This paper introduces a true multiclass formulation based on multinomial logistic regression and derives fast exact algorithms for learning sparse multiclass classifiers that scale favorably in both the number of training samples and the feature dimensionality, making them applicable even to large data sets in high-dimensional feature spaces.
Journal Article
Multi-Task Learning for Classification with Dirichlet Process Priors
TL;DR: Experimental results on two real life MTL problems indicate that the proposed algorithms automatically identify subgroups of related tasks whose training data appear to be drawn from similar distributions are more accurate than simpler approaches such as single-task learning, pooling of data across all tasks, and simplified approximations to DP.
Proceedings Article
On Ranking in Survival Analysis: Bounds on the Concordance Index
TL;DR: It is shown that classical survival analysis involving censored data can naturally be cast as a ranking problem, and two bounds on CI are devised, one of which emerges directly from the properties of PH models-and optimize them directly.
Proceedings Article
Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
TL;DR: The 2016 ACM Conference on Knowledge Discovery and Data Mining (KDD'16) as mentioned in this paper has attracted a significant number of submissions from countries all over the world, in particular, the research track attracted 784 submissions and the applied data science track attracted 331 submissions.
Proceedings Article
Bayesian Co-Training
TL;DR: In this article, a Bayesian undirected graphical model for co-training is proposed, which makes explicit the previously unstated assumptions of a large class of cotraining type algorithms, and also clarifies the circumstances under which these assumptions fail.