Michael J O'Neill Assistant Professor

Research

My research focuses on the design, analysis and implementation of continuous, nonlinear optimization methods.

Highlighted Publications

Worst-case complexity of an SQP method for nonlinear equality constrained stochastic optimization
Worst-case complexity of an SQP method for nonlinear equality constrained stochastic optimization
Frank E. Curtis, Michael J. O’Neill, Daniel P. Robinson
Mathematical Programming   ·   07 Jun 2023   ·   doi:10.1007/s10107-023-01981-1

All

2023

Worst-case complexity of an SQP method for nonlinear equality constrained stochastic optimization
Worst-case complexity of an SQP method for nonlinear equality constrained stochastic optimization
Frank E. Curtis, Michael J. O’Neill, Daniel P. Robinson
Mathematical Programming   ·   07 Jun 2023   ·   doi:10.1007/s10107-023-01981-1

2021

FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization
FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization
Dezhong Yao, Wanning Pan, Michael J O'Neill, Yutong Dai, Yao Wan, Hai Jin, Lichao Sun
arXiv   ·   01 Jan 2021   ·   doi:10.48550/ARXIV.2111.14655
A Stochastic Sequential Quadratic Optimization Algorithm for Nonlinear Equality Constrained Optimization with Rank-Deficient Jacobians
A Stochastic Sequential Quadratic Optimization Algorithm for Nonlinear Equality Constrained Optimization with Rank-Deficient Jacobians
Albert S. Berahas, Frank E. Curtis, Michael J. O'Neill, Daniel P. Robinson
arXiv   ·   01 Jan 2021   ·   doi:10.48550/ARXIV.2106.13015

2020

A log-barrier Newton-CG method for bound constrained optimization with complexity guarantees
A log-barrier Newton-CG method for bound constrained optimization with complexity guarantees
Michael O’Neill, Stephen J Wright
IMA Journal of Numerical Analysis   ·   18 Apr 2020   ·   doi:10.1093/imanum/drz074

2019

A Newton-CG algorithm with complexity guarantees for smooth unconstrained optimization
A Newton-CG algorithm with complexity guarantees for smooth unconstrained optimization
Clément W. Royer, Michael O’Neill, Stephen J. Wright
Mathematical Programming   ·   19 Jan 2019   ·   doi:10.1007/s10107-019-01362-7

2018

Behavior of accelerated gradient methods near critical points of nonconvex functions
Behavior of accelerated gradient methods near critical points of nonconvex functions
Michael O’Neill, Stephen J. Wright
Mathematical Programming   ·   26 Oct 2018   ·   doi:10.1007/s10107-018-1340-y

Note: JMLR publications cannot be automatically generated in the above style, so please check my google scholar (link at bottom of page) for a more complete list of publications.