SAHD 2014 - London

1st UCL-Duke University Workshop on Sensing and Analysis of High-Dimensional Data (SAHD), London 2014

The first UCL-Duke University Workshop on Sensing and Analysis of High-Dimensional Data, which acts as the European counterpart of the Biannual Duke University SAHD Workshop, aims to bring together leading researchers in the general fields of mathematics, statistics, computer science and engineering that work at the intersection of computational statistics, machine learning, signal processing, information and learning theory, and computer science, with the goal to advance the field of sensing, analysis and processing of high-dimensional data.

Categories

Top » Computer Science » Digital Signal Processing
Top » Computer Science » Machine Learning » Computational Learning Theory
Top » Computer Science » Information Theory
Top » Mathematics » Statistics
Top » Computer Science » Machine Learning » Deep Learning


Welcome
111 views, 05:31 WelcomeWelcome John Shawe-Taylor, Robert Calderbank, Miguel Rodrigues John Shawe-Taylor, Robert Calderbank, Miguel Rodrigues
Keynote
[syn] 3610 views, 1:07:18 Keynote Talk The Unreasonable Effectivness Of Deep LearningThe Unreasonable Effectivness Of Deep Learning Yann LeCun Yann LeCun
Invited Talks
[syn] 58 views, 26:27 Invited Talk Conjugate gradient iterative hard thresholding for compressed sensing and matrix completionConjugate gradient iterative hard thresholding for compressed sensing and matrix ... Jared Tanner Jared Tanner	[syn] 94 views, 27:04 Invited Talk Breaking the coherence barrier - A new theory for compressed sensingBreaking the coherence barrier - A new theory for compressed ... Anders Hansen Anders Hansen	[syn] 103 views, 29:39 Invited Talk Optimal compressive imaging for Fourier dataOptimal compressive imaging for Fourier data Gitta Kutyniok Gitta Kutyniok	[syn] 77 views, 26:24 Invited Talk Visual pattern encoding on the Poincaré sphereVisual pattern encoding on the Poincaré sphere Aleksandra Pizurica Aleksandra Pizurica 1 comment	[syn] 64 views, 28:00 Invited Talk Tracking dynamic point processes on networksTracking dynamic point processes on networks Rebecca Willett Rebecca Willett
[syn] 377 views, 31:05 Invited Talk Deep Gaussian processesDeep Gaussian processes Neil D. Lawrence Neil D. Lawrence	[syn] 650 views, 24:40 Invited Talk Mondrian forests: Efficient random forests for streaming data via Bayesian nonparametricsMondrian forests: Efficient random forests for streaming data via Bayesian ... Yee Whye Teh Yee Whye Teh	[syn] 198 views, 28:23 Invited Talk Beyond stochastic gradient descent for large-scale machine learningBeyond stochastic gradient descent for large-scale machine learning Francis R. Bach Francis R. Bach	[syn] 79 views, 29:19 Invited Talk Living on the edge: Phase transitions in convex programs with random dataLiving on the edge: Phase transitions in convex programs with ... Joel Tropp Joel Tropp	[syn] 259 views, 32:11 Invited Talk Building an automatic statisticianBuilding an automatic statistician Zoubin Ghahramani Zoubin Ghahramani
[syn] 386 views, 31:50 Invited Talk High-dimensional learning with deep network contractionsHigh-dimensional learning with deep network contractions Stéphane Mallat Stéphane Mallat
Panel
147 views, 1:02:35 Panel Big Data - Challenges and OpportunitiesBig Data - Challenges and Opportunities Patrick J. Wolfe, Robert Calderbank, et al. Patrick J. Wolfe, Robert Calderbank, Christoph Best, Christophe Bernard, Thore Graepel