Statistical Learning
Uniform convergence may be unable to explain generalization in deep learning
Vaishnavh Nagarajan, J. Zico Kolter
Neural Information Processing Systems http://nips.cc/
SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
Igor Fedorov, Ryan P. Adams, Matthew Mattina, Paul Whatmough
Neural Information Processing Systems http://nips.cc/
Random Tessellation Forests
Shufei Ge, Shijia Wang, Yee Whye Teh, Liangliang Wang, Lloyd Elliott
The flexibility of these methods is often limited bytherequirement thatthecutsbeaxisaligned.
Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks
Moreoever, we develop estimation theory providing tight control on the error of any estimated trajectory, indicating that the representations could even be used in quite noise-sensitive follow-on analyses.