Â鶹ӰԺ

Gongguo Tang; Department of Electrical, Computer, and Energy Engineering; Â鶹ӰԺGeometry and algorithm for some nonconvex optimizationsGreat progress has been made in the past few years in our understanding of nonconvex

Samy Wu Fung, Department of Applied Mathematics and Statistics, Colorado School of MinesEfficient Training of Infinite-depth Neural Networks via Jacobian-free BackpropagationA promising trend in deep learning replaces fixed depth models by

Pratyush Tiwary; Department of Chemistry & Biochemistry and Institute for Physical Science and Technology; University of MarylandFrom atoms to emergent dynamics (with help from statistical physics and artificial intelligence) ABSTRACT:The

Anindya De, Department of Computer and Information Science, University of PennsylvaniaTesting noisy linear functions for sparsityConsider the following basic problem in sparse linear regression -- an algorithm gets labeled samples of the form (x

Stephen Becker, Department of Applied Mathematics, Â鶹ӰԺStochastic Subspace Descent: Stochastic gradient-free optimization, with applications to PDE-constrained optimizationWe describe and analyze a family of algorithms that

Zhihui Zhu, Department of Electrical and Computer Engineering, University of DenverProvable Nonsmooth Nonconvex Approaches for Low-Dimensional ModelsAs technological advances in fields such as the Internet, medicine, finance, and remote sensing have

Amir Ajalloeian; Department of Electrical, Computer, and Energy Engineering; Â鶹ӰԺInexact Online Proximal-gradient Method for Time-varying Convex OptimizationThis paper considers an online proximal-gradient method to track

Sriram Sankaranarayanan, Department of Computer Science, Â鶹ӰԺReasoning about Neural Feedback SystemsData-driven components such as feedforward neural networks are increasingly being used in critical safety systems such

Mohsen Imadi; Department of Computer Science and Engineering; University of California, San Diego Towards Learning with Brain Efficiency Modern computing systems are plagued with significant issues in efficiently performing learning tasks. In this

Alec Dunton, Department of Applied Mathematics, Â鶹ӰԺ Learning a kernel matrix for nonlinear dimensionality reduction (Weinberger et. al. 2004) We investigate how to learn a kernel matrix for high dimensional data that lies