Coin Betting for Backprop without Learning Rates and More
- đ¤ Speaker: Francesco Orabona, Stony Brook University
- đ Date & Time: Thursday 24 August 2017, 13:00 - 14:00
- đ Venue: Auditorium, Microsoft Research Ltd, 21 Station Road, Cambridge, CB1 2FB
Abstract
Deep learning methods achieve state-of-the-art performance in many application scenarios. Yet, these methods require a significant amount of hyperparameters tuning in order to achieve the best results. In particular, tuning the learning rates in the stochastic optimization process is still one of the main bottlenecks. In this talk, I will propose a new stochastic gradient descent procedure that does not require any learning rate setting. Contrary to previous methods, we do not adapt the learning rates nor we make use of the assumed curvature of the objective function. Instead, we reduce the optimization process to a game of betting on a non-stochastic coin and we propose an optimal strategy based on a generalization of Kelly betting. Moreover, I’ll show how this reduction can be also used for other machine learning problems. Theoretical convergence is proven for convex and quasi-convex functions and empirical evidence shows the advantage of our algorithm over popular stochastic gradient algorithms
Series This talk is part of the Frontiers in Artificial Intelligence Series series.
Included in Lists
- All Talks (aka the CURE list)
- Auditorium, Microsoft Research Ltd, 21 Station Road, Cambridge, CB1 2FB
- bld31
- Cambridge Centre for Data-Driven Discovery (C2D3)
- Cambridge talks
- Chris Davis' list
- Datalog for Program Analysis: Beyond the Free Lunch
- Frontiers in Artificial Intelligence Series
- Guy Emerson's list
- Interested Talks
- Microsoft Research Cambridge, public talks
- ndk22's list
- ob366-ai4er
- Optics for the Cloud
- personal list
- PMRFPS's
- rp587
- School of Technology
- Trust & Technology Initiative - interesting events
- yk449
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)

Francesco Orabona, Stony Brook University
Thursday 24 August 2017, 13:00-14:00