University of Birmingham > Talks@bham > Optimisation and Numerical Analysis Seminars > Using second-order information in training large-scale machine learning models.

## Using second-order information in training large-scale machine learning models.Add to your list(s) Download to your calendar using vCal - Katya Scheinberg (Lehigh University, Pennsylvania, USA)
- Wednesday 14 June 2017, 12:00-13:00
- Nuffield G22.
If you have a question about this talk, please contact Sergey Sergeev. We will give a broad overview of the recent developments in using deterministic and stochastic second-order information to speed up optimization methods for problems arising in machine learning. Specifically, we will show how such methods tend to perform well in convex setting but often fail to provide improvement over simple methods, such as stochastic gradient descent, when applied to large-scale nonconvex deep learning models. We will discuss the difficulties faced by quasi-Newton methods that rely on stochastic first order information and Hessian-Free methods that use stochastic second order information. We will then give an overview of some recent theoretical results for optimization methods based of stochastic information. This talk is part of the Optimisation and Numerical Analysis Seminars series. ## This talk is included in these lists:Note that ex-directory lists are not shown. |
## Other listsMedical Imaging Research Seminars Algebra Seminar Geometry and Mathematical Physics seminar## Other talksUltrafast, all-optical, and highly efficient imaging of molecular chirality Hodge Theory: Connecting Algebra and Analysis Perfect matchings in random sparsifications of Dirac hypergraphs TBC Quantum simulations using ultra cold ytterbium Geometry of alternating projections in metric spaces with bounded curvature |