About Me

I am quantitative researcher at Citadel Securities. Previously, I was a postdoctoral associate at the MIT Laboratory for Information & Decision Systems, where I was hosted by Ali Jadbabie , Devavrat Shah , and Suvrit Sra . I completed my PhD studies under the supervision of Michael I. Jordan and Benjamin Recht in the Department of Computer Science at University of California, Berkeley, and I received a bachelor's degree in Mathematics from Princeton University, where I was advised by Sébastien Bubeck.

My academic research focused on the foundations of machine learning and connections with reinforcement learning and control theory.

Papers

For an updated list also check my Google scholar profile.

Model Predictive Control via On-Policy Imitation Learning
Kwangjun Ahn, Zakaria Mhammedi, Horia Mania, Zhang-Wei Hong, Ali Jadbabaie;
Learning for dynamics and control (L4DC) 2023.

Time varying regression with hidden linear dynamics
Ali Jadbabaie, Horia Mania, Devavrat Shah, Suvrit Sra;
Learning for dynamics and control (L4DC) 2022.

Active Learning for Nonlinear System Identification with Guarantees
Horia Mania, Michael I. Jordan, Benjamin Recht;
Journal of Machine Learning Research (JMLR) 2022.

Bandit Learning in Decentralized Matching Markets
Lydia Liu, Feng Ruan, Horia Mania, Michael I. Jordan;
Journal of Machine Learning Research (JMLR) 2021.

Why do classifier accuracies show linear trends under distribution shift?
Horia Mania, Suvrit Sra; 2020.

Evaluating Machine Accuracy on ImageNet
Vaishaal Shankar, Rebecca Roelofs, Horia Mania, Alex Fang, Benjamin Recht, Ludwig Schmidt;
International Conference on Machine Learning (ICML); 2020.

Competing Bandits in Matching Markets
Lydia T. Liu, Horia Mania, Michael I. Jordan;
International Conference on Artificial Intelligence and Statistics (AISTATS); 2020.

Certainty Equivalence is Efficient for Linear Quadratic Control
Horia Mania, Stephen Tu, Benjamin Recht;
Advances in Neural Information Processing Systems (NeurIPS); 2019.

Model Similarity Mitigates Test Set Overuse
Horia Mania, John Miller, Ludwig Schmidt, Moritz Hardt, Benjamin Recht;
Advances in Neural Information Processing Systems (NeurIPS); 2019.

On the Sample Complexity of the Linear Quadratic Regulator
Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, Stephen Tu;
Foundations of Computational Mathematics (FOCM); 2019.

Simple random search of static linear policies is competitive for reinforcement learning
Horia Mania, Aurelia Guy, Benjamin Recht;
Advances in Neural Information Processing Systems (NeurIPS); 2018.

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator
Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, Stephen Tu;
Advances in Neural Information Processing Systems (NeurIPS); 2018.

Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
Max Simchowitz, Horia Mania, Stephen Tu, Michael I. Jordan, Benjamin Recht;
Conference on Learning Theory (COLT); 2018.

On kernel methods for covariates that are rankings
Horia Mania, Aaditya Ramdas, Martin J. Wainwright, Michael I. Jordan, Benjamin Recht;
Electronic Journal of Statistics; 2018.

Perturbed Iterate Analysis for Asynchronous Stochastic Optimization
Horia Mania, Xinghao Pan, Dimitris Papailiopoulos, Benjamin Recht, Kannan Ramchandran, Michael I. Jordan;
SIAM Journal on Optimization; 2017.

On paths, stars and wyes in trees
Sébastien Bubeck, Katherine Edwards, Horia Mania, Cathryn Supko; 2016.

Wilmes' Conjecture and Boundary Divisors
Horia Mania; 2012.