SEN NA
SEN NA
Home
Research
Papers
Service
Misc
Contact
CV
Light
Dark
Automatic
stat.ML
Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems
We propose a trust-region stochastic sequential quadratic programming algorithm (TR-StoSQP) to solve nonlinear optimization problems …
Yuchen Fang
,
Sen Na
,
Michael W. Mahoney
,
Mladen Kolar
Cite
arXiv
An Asymptotically Optimal Method for Constrained Stochastic Optimization
We perform statistical inference for the solution of stochastic optimization problems with equality and box inequality constraints. The …
Sen Na
,
Yihang Gao
,
Michael K. Ng
,
Michael W. Mahoney
Cite
PDF
Online Covariance Matrix Estimation in Stochastic Inexact Newton Methods
Online algorithms gain prominence as the volume of data explodes, among which second-order methods are known for their robustness. …
Wei Kuang
,
Sen Na
,
Michael W. Mahoney
,
Mihai Anitescu
Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
We consider solving equality-constrained nonlinear, nonconvex optimization problems. This class of problems appears widely in a variety …
Ilgee Hong
,
Sen Na
,
Michael W. Mahoney
,
Mladen Kolar
Cite
arXiv
Inequality Constrained Stochastic Nonlinear Optimization via Active-Set Sequential Quadratic Programming
We study nonlinear optimization problems with a stochastic objective and deterministic equality and inequality constraints, which …
Sen Na
,
Mihai Anitescu
,
Mladen Kolar
Cite
DOI
arXiv
Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models
We design a trust-region sequential quadratic programming (TR-SQP) method to find both
first- and second-order
stationary points for …
Yuchen Fang
,
Sen Na
,
Michael W. Mahoney
,
Mladen Kolar
A Theoretically Sound Sequential Quadratic Programming Algorithm On Riemannian Manifolds
We design a Sequential Quadratic Programming (SQP) algorithm for solving equality-constrained optimization problems on Riemannian …
Miao Li
,
Sen Na
,
Mladen Kolar
Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence
We consider minimizing a smooth and strongly convex objective function using a stochastic Newton method. At each iteration, the …
Sen Na
,
Michał Dereziński
,
Michael W. Mahoney
Cite
DOI
arXiv
An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangians
We consider solving nonlinear optimization problems with a stochastic objective and deterministic equality constraints. We assume for …
Sen Na
,
Mihai Anitescu
,
Mladen Kolar
Cite
DOI
arXiv
Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic Programming
We consider statistical inference of equality-constrained stochastic nonlinear optimization problems. We develop a fully online …
Sen Na
,
Michael W. Mahoney
Cite
arXiv
»
Cite
×