About me
I am postdoctoral scholar mentored by Rina Foygel Barber at Department of Statistics, University of Chicago.
Prior to that, I obtained my PhD in Algorithms, Combinatorics and Optimization at the School of Industrial and Systems Engineering, Georgia Tech, where I was advised by Ashwin Pananjady.
Contact
mlou30 (at) uchicago (dot) edu
Research Interests
I am broadly interested in problems at the intersection of statistics and optimization. My previous work has focused on : (1) understanding the learning dynamics of iterative algorithms in non-convex statistical learning, and (2) developing average-case reductions between statistical models to establish statistical–computational tradeoffs.
Papers
(* denotes equal contribution)
Efficient reductions from a Gaussian source with applications to statistical-computational tradeoffs
Mengqi Lou, Guy Bresler, Ashwin Pananjady. arXiv:2510.07250
Under review at Annals of Statistics
IMS New Researcher Travel Awards 2026
Accurate, provable, and fast polychromatic tomographic reconstruction: A variational inequality approach
Mengqi Lou, Kabir Aladin Verchand, Sara Fridovich-Keil, Ashwin Pananjady. arXiv:2503.19925
SIAM Journal on Imaging Sciences
Computationally efficient reductions between some statistical models
Mengqi Lou, Guy Bresler, Ashwin Pananjady. arXiv:2402.07717
IEEE Transactions on Information Theory
Outstanding Paper Award in the Conference on Algorithmic Learning Theory 2025
Hyperparameter tuning via trajectory predictions: Stochastic prox-linear methods in matrix sensing
Mengqi Lou, Kabir Aladin Verchand, Ashwin Pananjady. arXiv:2402.01599
Mathematical Programming: Series B
Spotlight in the ICML 2023 workshop on High-dimensional Learning Dynamics
Alternating minimization for generalized rank-1 matrix sensing: Sharp predictions from a random initialization
Kabir Aladin Verchand*, Mengqi Lou*, Ashwin Pananjady. arXiv:2207.09660
Information and Inference: A Journal of IMA
Extended abstract in the Conference on Algorithmic Learning Theory 2024
Spotlight in the NeurIPS 2022 workshop on The Benefits of Higher-Order Optimization in Machine Learning
Do algorithms and barriers for sparse principal component analysis extend to other structured settings?
Guanyi Wang, Mengqi Lou, Ashwin Pananjady. arXiv:2307.13535
IEEE Transactions on Signal Processing
On seeded subgraph-to-subgraph matching: The ssSGM Algorithm and matchability information theory
Lingyao Meng, Mengqi Lou, Jianyu Lin, Vince Lyzinski, Donniell E. Fishkind. arXiv:2306.04016
Journal of Computational and Graphical Statistics