
-
Physarum Powered Differentiable Linear Programming Layers and Applications
Consider a learning algorithm, which involves an internal call to an opt...
read it
-
FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret
Algorithmic decision making based on computer vision and machine learnin...
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...
read it
-
Robust Blind Deconvolution via Mirror Descent
We revisit the Blind Deconvolution problem with a focus on understanding...
read it
-
Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
A number of results have recently demonstrated the benefits of incorpora...
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...
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...
read it
-
On the interplay of network structure and gradient convergence in deep learning
The regularization and output consistency behavior of dropout and layer-...
read it