Mathematics of AI       


Mathematics of AI - overview

This is the homepage of the IBM Mathematics of AI group. The group focuses on developing novel technologies leveraging Mathematics and its intersection with areas such as AI, Physics, and Quantum Computing.


  • Lior Horesh (group manager)
    Manager of the Mathematics of AI group of WRC. He is also an Adjunct Associate Professor in the Computer Science department of Columbia University, teaching graduate level advanced Machine Learning and Quantum Computing courses. His expertise lies at large-scale modeling, inverse problems, tensor algebra, experimental design, machine learning and quantum computing.

  • Amir Abboud
    Complexity theory, hardness in P, fine-grained complexity.

  • Vernon Austel

  • Francisco Barahona
    Optimization, algorithmic game theory, machine learning.

  • Ken Clarkson
    Matrix computations, computational geometry, algorithms, optimization.

  • Sanjeeb Dash
    Discrete optimization, integer and linear programming, with applications in interpretable machine learning.

  • Soumyadip Ghosh
    Stochastic optimization algorithms for decision making under uncertainty, with applications in machine learning to train large heterogeneous deep neural network models from areas such as speech recognition and natural language processing; Distributionally robust[DR] optimization, for example DR training of AI models.
  • Tayfun Gokmen

  • Joao Goncalves

  • Oktay Gunluk
    Mixed-integer programming, combinatorial optimization, multicommodity flows. Modeling, optimization and computation.

  • Anshul Gupta
    Sparse matrix algorithms, parallel direct sparse solvers, preconditioners for Krylov subspace methods, HPC.

  • Wilfried Haensch

  • Phokion Kolaitis
    Logic in computer science, computational complexity, database theory.
  • Vanessa Lopez-Marrero
    Computational and applied mathematics, computational science and engineering.

  • Yingdong Lu
    Computational and applied mathematics, stochastic processes and models.

  • Nimrod Megiddo
    Optimization, machine learning.

  • Tomasz Nowicki

  • Krzysztof Onak
    Algorithms for big data, massive parallel computation, sublinear algorithms, theory of computer science.

  • Parikshit Ram
    Large scale algorithms, similarity search, kernel methods, automated machine learning and data science.

  • Malte Rasch
    Algorithms for and simulation of analog AI hardware, neuromorphic computing, computational neuroscience.

  • Mattia Rigotti
    Training algorithms for neural networks, neuromorphic computing, computational neuroscience.

  • Alberto Sassi

  • Mark Squillante

  • Thomas Steinke
    Differential privacy, pseudorandomness, adaptive data analysis.

  • Barry Trager
    Symbolic computation, error correcting codes, computational algebraic geometry.

  • Yuhai Tu

  • Shashanka Ubaru (Goldstine Postdoctoral Fellow)
    Machine learning, numerical linear algebra, error correcting codes.

  • Chai Wah Wu
    Image processing, dynamical systems, synchronization and control of chaotic and networked systems.


Former permanent members: Roy Adler, Ramesh Agarwal, Haim Avron, Nikhil Bansal, Bob Brayton, Andrew Conn, Dan Connors, Don Coppersmith, JP Fasano, Lisa Fleisher, David Gamarnik, John Gunnels, Fred Gustavson, Alan Hoffman, Raya Horesh, Giuseppe Italiano, Satyen Kale, Anju Kambadur, Aida Khajavirad, Tracy Kimbrel, Bruce Kitchens, Laszlo Ladanyi, Jon Lee, Leo Liberti, Konstantin Makarychev, Viswanath Nagarajan, Giacomo Nannicini, Bob Risch, Ted Rivlin, Katya Scheinberg, Baruch Schieber, Mike Shub, Gregory Sorkin, Madhu Sudan, Maxim Sviridenko, Charles Tresser, Andreas Waechter, David Williamson, Shmuel Winograd, Laura Wynter.

Former postdocs (including Goldstine Fellows): Michael Kapralov, Rishi Saket, Shay Solomon.