1 citations · 1 across the 5 of their papers we have counts for
7 papers
REALM: Regime-Switching, Explainable, and Activation-Induced Linear Models
Xiaoran Cheng, Sen Na, Jia Li
Deep ReLU networks are piecewise-affine mappings that partition the input space into cells, each characterized by a distinct activation pattern. This structure motivates fitting a…
Inference of Online Newton Methods with Nesterov's Accelerated Sketching
Haoxuan Wang, Xinchen Du, Sen Na
Reliable decision-making with streaming data requires principled uncertainty quantification of online methods. While first-order methods enable efficient iterate updates, their inf…
Overlapping Schwarz Scheme for Linear-Quadratic Programs in Continuous Time
Hongli Zhao, Mihai Anitescu, Sen Na
We present an optimize-then-discretize framework for solving linear-quadratic optimal control problems (OCP) governed by time-inhomogeneous ordinary differential equations (ODEs).…
Online Covariance Matrix Estimation in Sketched Newton Methods
Wei Kuang, Mihai Anitescu, Sen Na
Given the ubiquity of streaming data, online algorithms have been widely used for parameter estimation, with second-order methods particularly standing out for their efficiency and…
Online Covariance Estimation in Nonsmooth Stochastic Approximation
Liwei Jiang, Abhishek Roy, Krishna Balasubramanian +3
We consider applying stochastic approximation (SA) methods to solve nonsmooth variational inclusion problems. Existing studies have shown that the averaged iterates of SA methods e…
Physics-Informed Neural Networks with Trust-Region Sequential Quadratic Programming
Xiaoran Cheng, Sen Na
Physics-Informed Neural Networks (PINNs) represent a significant advancement in Scientific Machine Learning (SciML), which integrate physical domain knowledge into an empirical los…
Parallel Sequential Quadratic Programming with Overlapping Graph Decomposition and Exact Augmented Lagrangian
Runxin Ni, Haoxuan Wang, Sen Na +2
In this paper, we address the challenge of solving large-scale graph-structured nonlinear programs (gsNLPs) in a scalable manner. GsNLPs are problems in which the objective and con…