Country
On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms Anonymous Author(s) Affiliation Address email
While there has been much attention on the theoretical aspect of the traditional i.i.d.
On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms Lam M. Nguyen
Stochastic gradient descent (SGD) algorithm is the method of choice in many machine learning tasks thanks to its scalability and efficiency in dealing with large-scale problems. In this paper, we focus on the shuffling version of SGD which matches the mainstream practical heuristics. We show the convergence to a global solution of shuffling SGD for a class of non-convex functions under over-parameterized settings.
Entropic Neural Optimal Transport via Diffusion Processes
We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between continuous probability distributions which are accessible by samples. Our algorithm is based on the saddle point reformulation of the dynamic version of EOT which is known as the Schrรถdinger Bridge problem. In contrast to the prior methods for large-scale EOT, our algorithm is end-to-end and consists of a single learning step, has fast inference procedure, and allows handling small values of the entropy regularization coefficient which is of particular importance in some applied problems. Empirically, we show the performance of the method on several large-scale EOT tasks.
On Convergence of Polynomial Approximations to the Gaussian Mixture Entropy
Gaussian mixture models (GMMs) are fundamental to machine learning due to their flexibility as approximating densities. However, uncertainty quantification of GMMs remains a challenge as differential entropy lacks a closed form.
The Best Noise-Canceling Headphones for Traveling Are 50 Off
With excellent noise canceling, the QuietComfort Ultra 2 would love to join you on your next long-haul flight. Our favorite pair of wireless headphones for traveling are currently marked down by $50. You can pick up the Bose QuietComfort Ultra 2 from Amazon for just $399 in both Black and Driftwood Sand, with the other colors remaining at their full price. Bose is known for incredible active noise canceling, and the latest generation of QuietComfort over-ear headphones is no different. Our reviewer Ryan Waniata was extremely impressed with the Bose, despite only minor upgrades, and considers them among the top three headsets when it comes to ANC, rivaled only by Sony's WH-1000XM6 and Bose's first-generation QuietComfort Ultra .