| Title | : | Large-scale Structured Low-rank Matrix Learning |
| Speaker | : | Pratik Jawanpuria (Amazon) |
| Details | : | Mon, 7 Aug, 2017 3:00 PM @ Alan M Turing Hall ( |
| Abstract: | : | We propose a novel optimization approach for learning a low-rank matrix which is also constrained to lie in a linear subspace. Exploiting a particular variational characterization of the squared trace norm regularizer, we formulate the structured low-rank matrix learning problem as a rank-constrained saddle point minimax problem. The proposed modeling decouples the low-rank and structural constraints onto separate factors. The optimization problem is formulated on the Riemannian spectrahedron manifold, where the Riemannian framework allows to propose computationally efficient conjugate gradient and trust-region algorithms. Our approach easily accommodates popular non-smooth loss functions, e.g., $ell_1$-loss, and our algorithms are scalable to large-scale problem instances. The numerical comparisons show that our proposed algorithms outperform state-of-the-art algorithms in standard and robust matrix completion, stochastic realization, and multi-task feature learning problems on various benchmarks.
Speaker Bio: Pratik Jawanpuria is an applied scientist at Amazon. He belongs to the Core Machine Learning team. He completed his B.Tech in Computer Science and Ph.D. from IIT Bombay. He then worked as a postdoctoral researcher at Saarland University. His research interests lie in the areas of machine learning and optimization. |
