AIMS Home

Interplays between Statistical Learning and Optimization

Organizer(s):
Name:	Affiliation:	Country:
Qiang Wu	Middle Tennessee State University	USA
Xuemei Chen	University of North Carolina Wilmington	USA
Yiming Ying	SUNY Albany	USA

Abstract:

The recent exchange between statistical learning and computational optimization has never been so fruitful. Merging techniques from learning theory, approximation theory, and numerical optimization, researchers nowadays try to understand the convergence dynamics of the optimization procedure and unveil the generalization mystery of learning algorithms as well as the intimate interaction between them. The objective of this session is to identify the recent progress and trends in statistical learning and optimization and to serve as a multi-disciplinary forum to promote interaction among researchers from statistical learning and applied mathematics to exchange new ideas and techniques.

List of approved abstract
Name	Affiliation	Title
Yunlong Feng	SUNY Albany	On learning with bounded loss functions
Shu Liu	Middle Tennessee State University	Pairwise Learning for Imbalanced Data Classification
Nicholas F Marshall	Oregon State University	Learning rates, corrupted linear systems, and randomized Kaczmarz
Matthew B Ogden	Middle Tennessee State University	Exploring Dynamical Parameters of Interacting Galaxies Using Deep Learning and Optimization
Ebenezer Oluwasakin	Middle Tennessee State University	Data-driven Deep Learning Neural Networks for Predicting the Number of Individuals Infected by COVID-19 Omicron Variant
Alex Powell	Vanderbilt University	Dynamical sampling: dynamical duals and quantization
Xingping Sun	Missouri State University	Kernel Interpolation of high dimensional scatter data
Qiang Wu	Middle Tennessee State University	An introduction to distributed machine learning
Yiming Ying	State University of New York at Albany	Learning Theory for Contrastive Representation Learning
Tian-Yi Zhou	Georgia Institute of Technology	Learning Ability of Interpolating Deep Convolutional Neural Networks