Research Interests
Primarily in Machine Learning, Optimization and their applications. Current work focuses on proposing optimization formulations for kernel learning under various set-ups (for e.g. Multiple Kernel Learning, Multi-task Learning, Rule Learning) and efficient algorithms for solving them.
Refereed Publications
- Pratik Jawanpuria, Manik Varma and J. Saketha Nath. On p-norm Path Following in Multiple Kernel Learning for Non-linear Feature Selection. accepted at ICML14
- Pratik Jawanpuria, J. Saketha Nath and Ganesh Ramakrishnan. Generalized Hierarchical Kernel Learning. (under review in Journal of Machine Learning Research). Paper link pdf. Code link
- Pratik Jawanpuria and J. Saketha Nath. A Convex Feature Learning Formulation for Latent Task Structure Discovery. ICML-2012. Paper link pdf. Code link tar.gz. Supplementary material
- Pratik Jawanpuria, J. Saketha Nath and Ganesh Ramakrishnan. Efficient Rule Ensemble Learning using Hierarchical Kernels. ICML-2011. Paper link pdf. Code link tar.gz. Techical report
- Pratik Jawanpuria and J. Saketha Nath. Multi-task Multiple Kernel Learning. SDM-2011. Paper link pdf
contact: <my name>DOT<first letter of my family name> AT cse DOT iitb DOT ac DOT in