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 > Statistics > Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression

## Harder, Better, Faster, Stronger Convergence Rates for Least-Squares RegressionAdd to your list(s) Download to your calendar using vCal - Francis Bach (INRIA)
- Friday 07 October 2016, 16:00-17:00
- MR12, Centre for Mathematical Sciences, Wilberforce Road, Cambridge..
If you have a question about this talk, please contact Quentin Berthet. We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first algorithm that achieves jointly the optimal prediction error rates for least-squares regression, both in terms of forgetting of initial conditions in O(1/n^2), and in terms of dependence on the noise and dimension d of the problem, as O(d/n). Our new algorithm is based on averaged accelerated regularized gradient descent, and may also be analyzed through finer assumptions on initial conditions and the Hessian matrix, leading to dimension-free quantities that may still be small while the “optimal” terms above are large. In order to characterize the tightness of these new bounds, we consider an application to non-parametric regression and use the known lower bounds on the statistical performance (without computational limits), which happen to match our bounds obtained from a single pass on the data and thus show optimality of our algorithm in a wide variety of particular trade-offs between bias and variance. (joint work with Aymeric Dieuleveut and N. Flammarion) This talk is part of the Statistics series. ## This talk is included in these lists:- All CMS events
- All Talks (aka the CURE list)
- CMS Events
- Cambridge Big Data
- Cambridge Forum of Science and Humanities
- Cambridge Language Sciences
- Chris Davis' list
- DPMMS Lists
- DPMMS info aggregator
- DPMMS lists
- Guy Emerson's list
- MR12, Centre for Mathematical Sciences, Wilberforce Road, Cambridge.
- Machine Learning
- School of Physical Sciences
- Statistical Laboratory info aggregator
- Statistics
- Statistics Group
- Trust & Technology Initiative - interesting events
- bld31
- ndk22's list
- rp587
Note that ex-directory lists are not shown. |
## Other listsCambridge Genomic Services Seminars Computer Laboratory Wednesday Seminars Security-related talks## Other talksDisabled Academics in the 21st Century: 15th Annual Disability Lecture CGHR Practitioner Series: Andrea Coomber, JUSTICE Predictive modeling of hydrogen assisted cracking – a Micromechanics conquest Introduction to early detection and tumour development Poland, Europe, Freedom: A Personal Reflection on the Last 40 Years “Soap cost a dollar”: Jostling with minds in economic contexts |