Miaolan Xie
Computer Science · Purdue University West Lafayette
Publications
20
Citations
66
Est. group size
—
Recurring co-author estimate
Active years
11
Publishing since 2016
Miaolan Xie works on the mathematical foundations of optimization algorithms used to train machine learning models, particularly methods that must cope with noisy or randomly sampled data (called 'stochastic' optimization). Much of this work develops theoretical guarantees—proofs about how quickly and reliably these algorithms converge—for methods like quasi-Newton, trust-region, and sequential quadratic programming approaches. The research also touches on feature selection (choosing which input variables matter most) and has some applied projects in reinforcement learning and computer graphics.
Publication output has grown over the past decade, with sparse activity before 2021 followed by a marked increase in recent years, including a notably high count projected for 2026.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- A Stochastic Quasi-Newton Method in the Absence of Common Random Numbers
Journal of Optimization Theory and Applications · 2026
- An Adaptive Proximal Framework for Weakly Convex Optimization with Unknown Parameter: Deterministic and Heavy-Tailed Stochastic Guarantees
arXiv (Cornell University) · 2026
- An Adaptive Proximal Framework for Weakly Convex Optimization with Unknown Parameter: Deterministic and Heavy-Tailed Stochastic Guarantees
arXiv (Cornell University) · 2026
- First- and Second-Order Stochastic Adaptive Regularization with Cubics: High-Probability Iteration and Sample Complexity
INFORMS Journal on Optimization · 2026
- PoseShield: Neural Collision Fields for Human Self-Collision Resolution
arXiv (Cornell University) · 2026
- A Sequential Quadratic Programming Method With High-Probability Complexity Bounds for Nonlinear Equality-Constrained Stochastic Optimization
SIAM Journal on Optimization · 2025
- Sample complexity analysis for adaptive optimization algorithms with stochastic oracles
Mathematical Programming · 2024
- High Probability Complexity Bounds for Adaptive Step Search Based on Stochastic Oracles
SIAM Journal on Optimization · 2024
- Stochastic Adaptive Regularization Method with Cubics: a High Probability Complexity Bound
2023
- A Sequential Quadratic Programming Method with High Probability Complexity Bounds for Nonlinear Equality Constrained Stochastic Optimization
arXiv (Cornell University) · 2023
- A Stochastic Quasi-Newton Method in the Absence of Common Random Numbers
arXiv (Cornell University) · 2023
- First- and Second-Order Stochastic Adaptive Regularization with Cubics: High Probability Iteration and Sample Complexity
arXiv (Cornell University) · 2023
- Sample Complexity Analysis for Adaptive Optimization Algorithms with Stochastic Oracles
arXiv (Cornell University) · 2023
- ControlBurn: Nonlinear Feature Selection with Sparse Tree Ensembles
arXiv (Cornell University) · 2022
- ControlBurn
2021
- arXiv (Cornell University)×12
- SIAM Journal on Optimization×2
- Mathematical Programming×1
- Journal of Optimization Theory and Applications×1
- UWSpace (University of Waterloo)×1
- Kaiyi Ji
Computer Science · The Ohio State University
- Anuran Makur
Computer Science · Purdue University West Lafayette
- Abolfazl Hashemi
Computer Science · Purdue University West Lafayette
- Haoyu Wang
Computer Science · Purdue University West Lafayette
- Gregory Dexter
Computer Science · Purdue University West Lafayette
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile