Convex Deep Learning via Normalized Kernels

29 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Federated Multi-Task Learning (2017, background): “While MOCHA does not apply to non-convex deep learning models in its current form, we note that there may be natural connections between this approach and “convexified” deep learning models [6, 34, 51, 56] in the context of kernelized federated multi-task learning.”
Recovery Guarantees for One-hidden-layer Neural Networks (2017, neutral): “(Aslan et al., 2014) transform NNs to convex semi-deﬁnite programming.”
Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks (2016, background): “A convex multi-layer architectures are developed in Aslan et al. (2014); Zhang et al. (2016).”
Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex (2018, background): “The goal of convexiﬁed linear neural networks is to relax the non-convex form of deep learning to the computable convex formulations [67, 3].”
Deep Online Convex Optimization by Putting Forecaster to Sleep (2015, background): “Aslan et al develop a convex multi-layer architecture (Aslan et al., 2013, 2014).”
Convexified Convolutional Neural Networks (2016, methodology): “[1, 2] propose a method for learning multi-layer latent variable models.”
Tensor Switching Networks (2016, background): “Convex learning and inference in various deep architectures can be found in [11, 12, 13] too.”