-
Channel-Directed Gradients for Optimization of Convolutional Neural Networks
We introduce optimization methods for convolutional neural networks that...
08/25/2020 ∙ by Dong Lao, et al. ∙
18
∙
share
read it
-
Local Saddle Point Optimization: A Curvature Exploitation Approach
Gradient-based optimization methods are the most popular choice for find...
05/15/2018 ∙ by Leonard Adolphs, et al. ∙
0
∙
share
read it
-
A Novel Representation of Neural Networks
Deep Neural Networks (DNNs) have become very popular for prediction in m...
10/05/2016 ∙ by Anthony Caterini, et al. ∙
0
∙
share
read it
-
Quantization based Fast Inner Product Search
We propose a quantization based approach for fast approximate Maximum In...
09/04/2015 ∙ by Ruiqi Guo, et al. ∙
0
∙
share
read it
-
Reducing the variance in online optimization by transporting past gradients
Most stochastic optimization methods use gradients once before discardin...
06/08/2019 ∙ by Sébastien M. R. Arnold, et al. ∙
0
∙
share
read it
-
BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model
Recent methods have significantly reduced the performance degradation of...
09/29/2020 ∙ by Junjie Liu, et al. ∙
0
∙
share
read it
-
Repulsive Curves
Curves play a fundamental role across computer graphics, physical simula...
06/14/2020 ∙ by Christopher Yu, et al. ∙
0
∙
share
read it
Sobolev Gradients for the Möbius Energy
05/15/2020 ∙ by Philipp Reiter, et al. ∙
0
∙
share
Aiming at optimizing the shape of closed embedded curves within prescribed isotopy classes, we use a gradient-based approach to approximate stationary points of the Möbius energy. The gradients are computed with respect to Sobolev inner products similar to the W^3/2,2-inner product. This leads to optimization methods that are significantly more efficient and robust than standard techniques based on L^2-gradients.
READ FULL TEXT
Comments
There are no comments yet.