Biography

I am Sina Baharlouei, a Ph.D. candidate studying operations research at the University of Southern California (USC). I am honored to have Professor Meisam Razaviyayn as my supervisor. My research interests include developing scalable and reliable optimization algorithms for machine learning applications, including Trustworthy AI (Fair and Robust Machine Learning), healthcare, and learning under adversarial and uncertain conditions.

CV

Google Scholar

Github

Twitter

LinkedIn

Publications

• Sina Baharlouei, Shivam Patel, and Meisam Razaviyayn. “f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization”. ICLR 2024, NeurIPS workshop on Optimization for Machine Learning 2023.

• Sina Baharlouei and Meisam Razaviyayn. “Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Framework”. NeurIPS workshop on Algorithmic Fairness through the Lens of Time 2023.

• Peng Dai, Sina Baharlouei, Taojian Tu, Bangyan L. Stiles, Meisam Razaviyayn, Sze-Chuan Suen . “Feature Selection in the Presence of Monotone Batch Effects.” ICML Workshop on Spurious Correlations, Invariance, and Stability, 2023, [Paper] [Code]

• Sina Baharlouei, Kelechi Ogudu, Sze-chuan Suen, and Meisam Razaviyayn. “RIFLE: Robust Inference from Low Order Marginals.” Transaction on Machine Learning Research (TMLR), 2023. [Paper] [Code]

• Sina Baharlouei, Fatemeh Sheikholeslami, Meisam Razaviyayn, and Zico Kolter: “Improving adversarial robustness via joint classification and multiple explicit detection classes.” 26th International Conference on Artificial Intelligence and Statistics AISTATS (2023). [Paper]

• Andrew Lowy*, Sina Baharlouei *, Rakesh Pavan, Meisam Razaviyayn, and Ahmad Beirami. “A Stochastic Optimization Framework for Fair Risk Minimization.” Transaction on Machine Learning Research (TMLR), 2022. [Paper] [Code]

• Sina Baharlouei, Meisam Razaviyayn, Elizabeth Tseng, and David Tse. “I-CONVEX: Fast and Accurate de Novo Transcriptome Recovery from Long Reads.” Data Science for Life Sciences Workshop ECML-PKDD (2022). [Paper] [Code]

• Sina Baharlouei, Maher Nouiehed, Ahmad Beirami, and Meisam Razaviyayn. “Rényi Fair Inference.” International Conference on Learning Representations (ICLR), 2020. [Paper] [Code]

• Maziar Sanjabi, Sina Baharlouei, Meisam Razaviyayn and Jason D. Lee. “When Does Non-Orthogonal Tensor Decomposition Have No Spurious Local Minima?”. [Paper]

Talks

• Session Chair at INFORMS 2023: “Fair and Robust Machine Learning in the Presence of Distribution Shifts.”

• Contributed Talk at INFORMS 2023: “Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Framework.”

• Contributed Talk at ICML 2023 Workshop on Duality Principles for Modern Machine Learning: “RIFLE: Robust Imputation and Inference from Low Order Marginals.”

• Invited Talk at Google Research, Sep 2022: “Fair and Robust Machine Learning Through Min-Max Optimization.”

• Contributed Talk at INFORMS 2022, “A Stochastic Optimization Framework for Fair Risk Minimization.”

• Contributed Talk at ICML 2021 Workshop on Socially Responsible Machine Learning: “FERMI: Fair Empirical Risk Minimization via Exponential Rényi Mutual Information.”