Search Results for author:
Found 10 papers, 2 papers with code
Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption
The capsule neural network (CapsNet), by Sabour, Frosst, and Hinton, is the first actual implementation of the conceptual idea of capsule neural networks.
Convexity Certificates from Hessians
The Hessian of a differentiable convex function is positive semidefinite.
Vectorized and performance-portable Quicksort
Recent works showed that implementations of Quicksort using vector CPU instructions can outperform the non-vectorized algorithms in widespread use.
Optimization for Classical Machine Learning Problems on the GPU
Here, we extend the GENO framework to also solve constrained optimization problems on the GPU.
A Simple and Efficient Tensor Calculus for Machine Learning
This leaves two options, to either change the underlying tensor representation in these frameworks or to develop a new, provably correct algorithm based on Einstein notation.
GENO -- GENeric Optimization for Classical Machine Learning
The framework is flexible enough to encompass most of the classical machine learning problems.
Ising Models with Latent Conditional Gaussian Variables
In the case of only a few latent conditional Gaussian variables these spurious interactions contribute an additional low-rank component to the interaction parameters of the observed Ising model.
Computing Higher Order Derivatives of Matrix and Tensor Expressions
Optimization is an integral part of most machine learning systems and most numerical optimization schemes rely on the computation of derivatives.
Distributed Convex Optimization with Many Convex Constraints
We address the problem of solving convex optimization problems with many convex constraints in a distributed setting.
Approximating Concavely Parameterized Optimization Problems
We consider an abstract class of optimization problems that are parameterized concavely in a single parameter, and show that the solution path along the parameter can always be approximated with accuracy $\varepsilon >0$ by a set of size $O(1/\sqrt{\varepsilon})$.
