Nina's Page

Maria-Florina Balcan

Cadence Design Systems Professor of Computer Science
School of Computer Science (MLD and CSD)
Carnegie Mellon University

Office: GHC 8205
Phone: 412-268-5295
Email: ninamf AT cs DOT cmu DOT edu

I am the Cadence Design Systems Professor of Computer Science at Carnegie Mellon University. My main research interests are in machine learning, artificial intelligence, theoretical computer science, algorithmic game theory, and novel connections between learning theory and other scientific fields (including optimization and operations research). Current research focus includes:

Theoretical underpinnings of modern artificial intelligence. These include reasoning, agents, and the design & analysis of practical data-driven algorithms for solving optimization problems.
New analyses and algorithms for machine learning, including deep learning, learning from limited supervision, learning representations, life-long learning, and AutoML. Also learnability of complex objects and processes.
Algorithm design and analysis including beyond the worst-case analysis of algorithms.
Computational and data-driven approaches in game theory and economics.
Computational, learning theoretic, and game theoretic aspects of multi-agent systems.

Honors and awards. I am an ACM Fellow, an AAAI Fellow, a Simons Investigator in Theoretical Computer Science, a recipient of the 2019 ACM Grace Murray Hopper Award (awarded to the outstanding young computer professional of the year), a Sloan Fellow, a Microsoft Faculty Fellow, a Kavli Fellow, a recipient of the NSF Career Award, and several industry awards.

Major service. I was a Program Committee Co-chair for NeurIPS 2020, ICML 2016, and COLT 2014, as well as the general chair for ICML 2021. I was a member of the Scientific Advisory Board of the Simons Institute for Theory of Computing (2023 - 2025). I was a Workshop and Tutorials Co-Chair for the IEEE Symposium on Foundations of Computer Science (FOCS) 2019 and 2020, and a Tutorial Co-Chair for the International Conference on Machine Learning (ICML) 2019.

For more information see my resume.

Research

List of all my papers here.

Selected talks. I have given numerous keynotes and high-profile talks across multiple disciplines, including AAMAS 2015, ITA 2018, Information Theory Workshop 2020, SAGT 2019, ECML-PKDD 2019, LATIN 2020, International Conference on Game Theory 2021, ACM Tech Talk 2021, ICM 2022, STACS 2022, Uhlenbeck Lecture (Program for Women and Mathematics) 2022, DeepMath 2023, ASL Lecture of JMM 2025. See below a couple of my recent talks.

Machine Learning Theory: New Challenges and Connections. ASL Lecture at the Joint Mathematics Meetings (JMM), 2025.
Robust and Reliable Machine Learning. DeepMath, 2023.
Learning Theoretic Foundations of Data-driven Algorithm Design. International Congress of Mathematicians, 2022.
Machine Learning for Algorithm Design. ACM Tech Talk 2021.

Selected tutorials.

New Frontiers of Hyperparameter Optimization: Recent advances and open challenges in theory and practice. Joint with Dravyansh Sharma and Colin White. NeurIPS 2025.
New Frontiers of Automated Mechanism Design for Pricing and Auctions. Joint with Tuomas Sandholm and Ellen Vitercik. AAAI 2021 and 2019, ACM-EC 2019, and ICML 2018.

Selected recent papers

Nearly-optimal bandit learning in stackelberg games with side information. With Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Keegan Harris, and Steven Wu. ICLR 2026.
On Learning Verifiers and Implications to Chain-of-Thought Reasoning. With Avrim Blum, Zhiyuan Li, and Dravyansh Sharma. NeurIPS 2025.
Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function. With Anh Tuan Nguyen and Dravyansh Sharma. NeruIPS 2025.
New Sequence-Independent Lifting Techniques for Cutting Planes and When They Induce Facets. With Siddharth Prasad, Ellen Vitercik, and Tuomas Sandholm. IJCAI 2025.
Generalization Guarantees for Multi-Item Profit Maximization: Pricing, Auctions, and Randomized Mechanisms With Tuomas Sandholm and Ellen Vitercik. Operations Research (OR) 2025.
Earlier version in EC 2018.
Learning Accurate and Interpretable Decision Trees. With Dravyansh Sharma. UAI 2024 (Oral). Winner of the Outstanding student paper award.
Also in the Best Papers from Sister Conferences Track at the International Joint Conference on Artificial Intelligence (IJCAI), 2025
Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances. With Mikhail Khodak, Edmond Chow, and Ameet Talwalkar. ICLR 2024 (Spotlgiht).
Regret Minimization in Stackelberg Games with Side Information. With Keegan Harris and Zhiwei Steven Wu. NeurIPS 2024.
How much data is sufficient to learn high-performing algorithms? With Dan DeBlasio, Travis Dick, Carl Kingsford, Tuomas Sandholm, and Ellen Vitercik. Journal of the ACM 2024.
Earlier version in STOC 2021.
Learning to Branch: Generalization Guarantees and Limits of Data-Independent Discretization. With Travis Dick, Tuomas Sandholm, and Ellen Vitercik. Journal of the ACM 2024.
Earlier version in ICML 2018.
Reliable learning in challenging environments.With Steve Hanneke, Rattana Pukdee, and Dravyansh Sharma. NeurIPS 2023.
Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts. With Siddharth Prasad, Tuomas Sandholm, and Ellen Vitercik. NeurIPS 2022 (Oral).
Robustly-reliable learners under poisoning attacks. With Avrim Blum, Steve Hanneke, Dravyansh Sharma. COLT 2022.
Data driven semi-supervised learning. With Dravyansh Sharma. NeurIPS 2021 (Oral).
Data-driven algorithm design. Chapter 29 in the Beyond the Worst-Case Analysis of Algorithms book, Cambridge University Press, 2020.
Noise in Classification. With Nika Haghtalab. Chapter 16 in the Beyond the Worst-Case Analysis of Algorithms book, Cambridge University Press, 2020.
Semi-bandit Optimization in the Dispersed Setting. With Travis Dick and Wesley Pegden. UAI 2020.
Learning to Link. With Travis Dick and Manuel Lang. ICLR 2020.
Adaptive Gradient-Based Meta-Learning Method. With Mikhail Khodak and Ameet Talwalkar. NeurIPS 2019.
Envy-free Classification. With Travis Dick, Ritesh Noothigattu, and Ariel D. Procaccia. NeurIPS 2019.
Estimating Approximate Incentive Compatibility. With Tuomas Sandholm and Ellen Vitercik. ACM EC 2019. Winner of the Exemplary Artificial Intelligence Track Paper Award.
Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization. With Travis Dick and Ellen Vitercik. FOCS 2018.
Data-Driven Clustering via Parameterized Lloyd's Families. With Travis Dick and Colin White. NeurIPS 2018 (Spotlight).
Submodular Functions: Learnability, Structure, and Optimization. With Nick Harvey. SIAM Journal of Computing 2018.
Earlier version titled Learning Submodular Functions in STOC 2011.
Also a NECTAR track paper at ECML-PKDD 2012 (for "significant machine learning results"). See short abstract.
Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems. With Vaishnavh Nagarajan, Ellen Vitercik, and Colin White. COLT 2017.
The Power of Localization for Learning Linear Separators with Noise. With Pranjal Awasthi and Phil Long. Journal of the ACM 2017.
Earlier version in STOC 2014.
Nash Equilibria in Perturbation-Stable Games. With Mark Braverman. Theory of Computing Journal 2017.
Clustering under Perturbation Resilience. With Yingyu Liang. SIAM Journal of Computing 2016.
Efficient Algorithms for Learning and 1-bit Compressed Sensing under Asymmetric Noise. With Pranjal Awasthi, Nika Haghtalab, and Hongyang Zhang. COLT 2016.
Statistical Active Learning Algorithms for Noise Tolerance and Differential Privacy. With Vitaly Feldman. Algorithmica 2015 (special issue, invited).
Earlier version in NIPS 2013.
Robust Hierarchical Clustering. With Yingyu Liang and Pramod Gupta. Journal of Machine Learning Research 2014.
Earlier version in COLT 2010.
Distributed Learning, Communication Complexity, and Privacy.. With Avrim Blum, Shai Fine, and Yishay Mansour. COLT 2012. Winner of the Runner Up Best Paper Award.
The True Sample Complexity of Active Learning. With Steve Hanneke and Jennifer Wortman. COLT 2008. Winner of the Mark Fulk Best Student Paper Award.

Teaching

10-422 Foundations of Learning, Game Theory, and Their Connections (at CMU). Spring 2026, Spring 2025, Spring 2024, and Spring 2023.
10-726 Machine Learning Theory: The Art of Problem Formulation and Theorem Proving (at CMU). Fall 2025 (with Max Simchowitz).
10-701 Machine Learning (at CMU): Spring 2022 (with Henry Chai), Fall 2024 (with Geoff Gordon).
10813 Advanced Topics in Machine Learning Theory (at CMU). Fall 2022.
10-315 Machine Learning (at CMU): Fall 2023, Spring 2021 (with Leila Wehbe), Spring 2019.
10-715 Advanced Introduction to Machine Learning (at CMU): Fall 2018, Fall 2017.
10-401 Machine Learning (at CMU): Spring 2018.
10-601 Machine Learning (at CMU): Fall 2016 (with Matt Gormley), Spring 2016 (with William Cohen), Spring 2015 (with Tom Mitchell).
10-806 Foundations of Machine Learning and Data Science (at CMU): Fall 2015 (with Avrim Blum).
Machine Learning Theory (at Georgia Tech): Fall 2013, Fall 2011, Spring 2010.
Design and Analysis of Algorithms (at Georgia Tech): Spring 2014, Spring 2013, Fall 2012, Spring 2011.
Connections between Learning, Game Theory, and Optimization (at Georgia Tech) Fall 2010.
Machine Learning Theory (at CMU). Spring 2007 (with Avrim Blum).
Artificial Intelligence (Spring 2002, University of Bucharest)