Andrew Lowy
I am a postdoctoral Research Associate in the Institute for Foundations of Data Science at UW-Madison, advised by Stephen J. Wright (UW-Madison), and working closely with Jonathan Ullman (Northeastern). I received my PhD in Applied Math at University of Southern California, advised by Meisam Razaviyayn. I was awarded the 2023 Center for Applied Mathematical Sciences (CAMS) Graduate Student Prize for excellence in research with a substantial mathematical component. Prior to attending USC, I received my B.A. in public policy and economics at Princeton University, and completed a post-bac in mathematics at Columbia University.
My research centers around privacy-preserving and fair machine learning and optimization. I especially enjoy understanding fundamental limits and developing scalable algorithms that attain these limits.
Publications
How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization [arXiv]
Andrew Lowy, Jonathan Ullman, Stephen J. Wright
International Conference on Machine Learning (ICML) 2024, to appear
Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
Changyu Gao, Andrew Lowy, Stephen J. Wright, Xingyu Zhao (alphabetical author order)
International Conference on Machine Learning (ICML) 2024, to appear
Optimal Differentially Private Model Training with Public Data [arXiv; Code]
Andrew Lowy, Zeman Li, Tianjian Huang, and Meisam Razaviyayn
International Conference on Machine Learning (ICML) 2024, to appear
Theory and Practice of Differential Privacy (TPDP) 2023
Why Does Differential Privacy with Large Epsilon Prevent Practical Membership Inference Attacks? [arXiv]
Andrew Lowy, Zhuohang Li, Jing Liu, Toshiaki Koike-Akino, Kieran Parsons, Ye Wang
Fifth AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-24)
Exploring User-level Gradient Inversion with a Diffusion Prior
Zhuohang Li, Andrew Lowy, Jing Liu, Toshiaki Koike-Akino, Bradley Malin, Kieran Parsons, Ye Wang
International Workshop on Federated Learning in the Age of Foundation Models at NeurIPS 2023
Private Stochastic Optimization With Large Worst-Case Lipschitz Parameter:
Optimal Rates for (Non-Smooth) Convex Losses and Extension to Non-Convex Losses [arXiv; Talk (starts at 21:45)]
Andrew Lowy and Meisam Razaviyayn
Algorithmic Learning Theory (ALT) 2023
Theory and Practice of Differential Privacy (TPDP) 2023 - Selected for Special Issue of Journal of Privacy and Confidentiality
Optimization for Machine Learning (OPT 2022) at NeurIPS 2022
Stochastic Differentially Private and Fair Learning [arXiv; Talk; Code]
Andrew Lowy, Devansh Gupta, and Meisam Razaviyayn
International Conference on Learning Representations (ICLR) 2023
Oral (top 6 papers) in AFCP 2022 at NeurIPS, PMLR 2022
Theory and Practice of Differential Privacy (TPDP) 2023
Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses [arXiv; Talk; Code]
Andrew Lowy and Meisam Razaviyayn
International Conference on Learning Representations (ICLR) 2023
Theory and Practice of Differential Privacy (TPDP) at ICML 2022
Private Non-Convex Federated Learning Without a Trusted Server [arXiv; Talk; Code]
Andrew Lowy, Ali Ghafelebashi, and Meisam Razaviyayn
International Conference on Artificial Intelligence and Statistics (AISTATS) 2023
Theory and Practice of Differential Privacy (TPDP) at ICML 2022
A Stochastic Optimization Framework for Fair Risk Minimization [arXiv; Talk; Code]
Andrew Lowy*, Sina Baharlouei*, Rakesh Pavan, Meisam Razaviyayn, and Ahmad Beirami (*= equal contribution)
Transactions on Machine Learning Research (TMLR), 2022
Contributed talk in Trustworthy and Socially Responsible ML (TSRML) at NeurIPS 2022
Efficient Search of First-Order Nash Equilibria in Nonconvex-Concave Smooth Min-Max Problems [arXiv]
Dmitrii Ostrovskii, Andrew Lowy, and Meisam Razaviyayn
SIAM Journal of Optimization, 2021
Output Perturbation for Differentially Private Convex Optimization [arXiv]
Andrew Lowy and Meisam Razaviyayn
Spotlight in AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-21)
Presentations
April 2024: IFDS IDEA Seminar, University of Wisconsin-Madison
November 2023: IFDS IDEA Seminar, University of Wisconsin-Madison
September 2023: 3 contributed posters at TPDP, Boston University
June 2023: Invited Talk at USDA's NASS ML Speaker Series, Virtual
April 2023: Invited Talk at Probability & Statistics Seminar, USC
Feb. 2023: Contributed Talk at ALT 2023, National University of Singapore, Singapore
Dec. 2022: 3 contributed presentations at NeurIPS 2022 (including one oral), New Orleans, LA
Oct. 2022: Invited Talk at USC-META REAL First Anniversary Event, USC
Sept. 2022: Invited Talk at MLOPT Idea Seminar [Zoom Recording], UW-Madison (Virtual)
July 2022: Invited Talk at ICCOPT, Lehigh University
July 2022: 2 contributed presentations at TPDP at ICML 2022, Baltimore, MD
March 2022: Invited Talk at USC-META REAL Workshop, USC
Mar. 2022: Invited Talk at Informs Optimization Society, Clemson University
Dec. 2021: New Frontiers in Federated Learning at NeurIPS 2021, Virtual
July 2021: Contributed Talk at Socially Responsible Machine Learning, ICML 2021, Virtual
Feb. 2021: Spotlight Talk at AAAI Workshop on Privacy-Preserving AI, Virtual
Nov. 2020. Invited Talk at Informs Annual Meeting, Virtual
Teaching Assistantships
Mathematical Statistics (Math 408, Fall 2021 with Steve Heilman)
Probability Theory (Math 407, Fall 2020 with Steve Heilman)
Calculus III (Math 226, Spring 2020 with Michael Hall)
Introductory Statistics (Math 114, Spring 2019 with Cindy Blois)
Differential Equations and Linear Algebra (Math 225, Fall 2019 with David Crombeque)
Calculus II (Math 126, Spring 2018/Fall 2018 with Nabil Ziane/Cymra Haskell)
Service
Conference Reviewer: ICML (2022 Outstanding Reviewer Award), NeurIPS, ICLR (2021/2022), AISTATS, COLT (2024)
Journal Reviewer: TMLR (2022 - Present)
Session Chair/Organizer: ICML 2022; Informs Optimization Society (IOS 2022)