World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
53
Citations
8955
World Ranking
4908
National Ranking
2280

Research.com Recognitions

  • 2019 - ACM Grace Murray Hopper Award For foundational and breakthrough contributions to minimally-supervised learning.
  • 2014 - Fellow of Alfred P. Sloan Foundation

Overview

Maria-Florina Balcan is affiliated with Carnegie Mellon University in the United States. Their research primarily spans the field of computer science, with a focus on several subfields including artificial intelligence, management science and operations research, computer networks and communications, computational theory and mathematics, and computer vision and pattern recognition.

Their work covers a variety of topics within machine learning and algorithms, such as machine learning and data classification, advanced bandit algorithms research, adversarial robustness in machine learning, auction theory and applications, constraint satisfaction and optimization, and optimization and search problems.

Selected recent publications by Maria-Florina Balcan include:

  • How Much Data Is Sufficient to Learn High-Performing Algorithms? (2024), Journal of the ACM
  • k -center Clustering under Perturbation Resilience (2020), ACM Transactions on Algorithms
  • Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond (2021), arXiv (Cornell University)

Other recent works associated with their collaborations include Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing (2021) published in arXiv (Cornell University).

Frequent coauthors of Maria-Florina Balcan include Tüomas Sandholm, Dravyansh Sharma, Ellen Vitercik, Mikhail Khodak, and Siddharth Prasad. These collaborations reflect a consistent engagement with colleagues across various areas of their research interests.

The venues where Maria-Florina Balcan has published with notable frequency are:

  • arXiv (Cornell University)
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Journal of the ACM
  • Cambridge University Press eBooks
  • ACM Transactions on Algorithms

Among professional recognitions, Maria-Florina Balcan received the ACM Grace Murray Hopper Award in 2019 for foundational contributions to minimally-supervised learning. They were also named a Fellow of the Alfred P. Sloan Foundation in 2014.

Best Publications

  • Agnostic active learning

    Maria-Florina Balcan;Alina Beygelzimer;John Langford

  • Margin based active learning

    Maria-Florina Balcan;Andrei Broder;Tong Zhang

  • Co-Training and Expansion: Towards Bridging Theory and Practice

    Maria-florina Balcan;Avrim Blum;Ke Yang

  • A theory of learning with similarity functions

    Maria-Florina Balcan;Avrim Blum;Nathan Srebro

  • Approximation Algorithms and Online Mechanisms for Item Pricing

    Maria-Florina Balcan;Avrim Blum

  • The true sample complexity of active learning

    Maria-Florina Balcan;Steve Hanneke;Jennifer Wortman Vaughan

  • Scalable Kernel Methods via Doubly Stochastic Gradients

    Bo Dai;Bo Xie;Niao He;Yingyu Liang

  • Kernels as features: On kernels, margins, and low-dimensional mappings

    Maria-Florina Balcan;Avrim Blum;Santosh Vempala

  • The True Sample Complexity of Active Learning.

    Maria-Florina Balcan;Steve Hanneke;Jennifer Wortman

  • A discriminative framework for clustering via similarity functions

    Maria-Florina Balcan;Avrim Blum;Santosh Vempala

  • Distributed Learning, Communication Complexity and Privacy

    Maria Florina Balcan;Avrim Blum;Shai Fine;Yishay Mansour

  • Learning submodular functions

    Maria-Florina Balcan;Nicholas J. A. Harvey

  • Approximate clustering without the approximation

    Maria-Florina Balcan;Avrim Blum;Anupam Gupta

  • Item pricing for revenue maximization

    Maria-Florina Balcan;Avrim Blum;Yishay Mansour

  • Robust hierarchical clustering

    Maria-Florina Balcan;Yingyu Liang;Pramod Gupta

  • The Power of Localization for Efficiently Learning Linear Separators with Noise

    Pranjal Awasthi;Maria Florina Balcan;Philip M. Long

  • Mechanism design via machine learning

    M.-F. Balcan;A. Blum;J.D. Hartline;Y. Mansour

  • Clustering under Perturbation Resilience

    Maria Florina Balcan;Yingyu Liang

  • Active and passive learning of linear separators under log-concave distributions

    Maria Florina Balcan;Philip M. Long

  • A discriminative model for semi-supervised learning

    Maria-Florina Balcan;Avrim Blum

  • Adaptive Gradient-Based Meta-Learning Methods

    Mikhail Khodak;Maria-Florina F. Balcan;Ameet S. Talwalkar

  • On a theory of learning with similarity functions

    Maria-Florina Balcan;Avrim Blum

  • Improved Distributed Principal Component Analysis

    Yingyu Liang;Maria-Florina F Balcan;Vandana Kanchanapally;David Woodruff

Frequent Co-Authors

Avrim Blum
Avrim Blum Toyota Technological Institute at Chicago
Yingyu Liang
Yingyu Liang University of Wisconsin–Madison
Tuomas Sandholm
Tuomas Sandholm Carnegie Mellon University
Yishay Mansour
Yishay Mansour Tel Aviv University
David P. Woodruff
David P. Woodruff Carnegie Mellon University
Le Song
Le Song Mohamed bin Zayed University of Artificial Intelligence
Shang-Hua Teng
Shang-Hua Teng University of Southern California
Mark Braverman
Mark Braverman Princeton University
Santosh Vempala
Santosh Vempala Georgia Institute of Technology
Philip M. Long
Philip M. Long Google (United States)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

When considering a career in Computer Science, it’s essential to explore your educational options to find the best path forward. Many students pursue online degrees for flexibility and affordability. For those starting out, earning an online associate's degree can be a practical first step, building foundational skills in programming and technology.

Affordability is another critical factor. Choosing one of the cheapest online degrees allows students to maximize their return on investment while minimizing student debt. Moving to graduate studies, a master’s in fields like computer science or data analytics ranks among the most valuable masters degrees, enhancing career prospects and potential earnings.

Concerns about academic history are also common. Some wonder if it’s possible to advance with a lower GPA. Fortunately, there are many best online colleges that accept low gpa, making further education in computer science accessible to a wider range of students.

Carefully researching these pathways ensures every student can design an educational plan that fits their needs and goals in tech.

Best Scientists Citing Maria-Florina Balcan

Trending Scientists