COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Information Geometry — Natural Gradient Descent
Information Geometry — Natural Gradient DescentAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact . Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders. Information geometry applies fundamental concepts of differential geometry to probability theory and statistics to study statistical manifolds, which are Riemannian manifolds in which each point in the manifold corresponds to a probability distribution. The perhaps most prominent application of information geometry in machine learning is natural gradient descent (NGD), which can be described as ‘gradient descent which respects the curvature of the statistical manifold’. In this session, we will be looking at NGD from different perspectives. In particular, we will consider NGD as 1) preconditioning the gradient with the inverse Fisher information matrix, 2) second-order optimisation with Newton’s method, 3) the result of stating gradient descent as a valid tensor equation, and (bonus) *) mirror descent in a dual Riemannian manifold. Previous knowledge of differential geometry is NOT required. Reading (suggested, but not required): Martens, J. (2020). “New Insights and Perspectives on the Natural Gradient Method”. Journal of Machine Learning Research, Volume 21, Issue 146. (Sections 5, 8 – 8.1, 9.2, 6 pages) Raskutti, G., Mukherjee, S. (2015). “The information geometry of mirror descent”. IEEE Transactions on Information Theory, Volume 61, Issue 3. (Sections 1, 2, 3 pages) This talk is part of the Machine Learning Reading Group @ CUED series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsArrol Adam Lecture SeriesOther talksQuantum Soliton Surprise How Salmonella reprogrammes a host kinase to drive macrophage polarisation Data Journalism & Audience Accessibility Networking Reception with Interactive Session (Chair: Timandra Harkness) The potentials and pitfalls of digital healthcare in the 21st Century Christmas Quiz |