-
Physarum Powered Differentiable Linear Programming Layers and Applications
Consider a learning algorithm, which involves an internal call to an opt...
04/30/2020 ∙ by Zihang Meng, et al. ∙
5
∙
share
read it
-
FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret
Algorithmic decision making based on computer vision and machine learnin...
04/03/2020 ∙ by Vishnu Suresh Lokhande, et al. ∙
0
∙
share
read it
-
Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization offers Significant Performance and Efficiency Gains
Data dependent regularization is known to benefit a wide variety of prob...
09/26/2019 ∙ by Sathya N. Ravi, et al. ∙
17
∙
share
read it
-
Robust Blind Deconvolution via Mirror Descent
We revisit the Blind Deconvolution problem with a focus on understanding...
03/21/2018 ∙ by Sathya N. Ravi, et al. ∙
0
∙
share
read it
-
Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
A number of results have recently demonstrated the benefits of incorpora...
03/17/2018 ∙ by Sathya N. Ravi, et al. ∙
0
∙
share
read it
-
A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees
We present a new Frank-Wolfe (FW) type algorithm that is applicable to m...
08/22/2017 ∙ by Sathya N. Ravi, et al. ∙
0
∙
share
read it
-
On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation
We study mechanisms to characterize how the asymptotic convergence of ba...
02/28/2017 ∙ by Vamsi K. Ithapu, et al. ∙
0
∙
share
read it
-
On the interplay of network structure and gradient convergence in deep learning
The regularization and output consistency behavior of dropout and layer-...
11/17/2015 ∙ by Vamsi K. Ithapu, et al. ∙
0
∙
share
read it
