Ian McPherson
  • About
    • News
    • Contact
  • Research
    • Research Areas
    • Publications and Presentations
  • Teaching
  • Blog
  • CV

Ian McPherson

E-mail LinkedIn ORCID

Welcome to my website! My name is Ian, and I am currently pursuing a PhD in Applied Mathematics and Statistics under the joint supervision of Mauro Maggioni and Mateo Díaz at Johns Hopkins University. I completed a MSc in Pure Mathematics at Tufts University, and two BAs in Economics and Biochemistry at Occidental College.

Research Interests

I exploit mathematical structures to design and analyze optimization algorithms, and construct statistical estimators from high-dimensional data.

I am interested in the theoretical and algorithmic foundations of Data Science, motivated by the impact of exploiting data for advancing scientific discovery. To exploit data, one must use fast/scalable algorithms while side-stepping the curse of dimensionality which negatively effects convergence and statistical rates.

To this end, I explore the interplay of optimization, geometry, and statistics through a variety of different mathematical lenses including Riemannian geometry, optimal transport, and high-dimensional probability.

Research Areas »

Research Pipeline

Below are some of my ongoing and recent research projects. For a full list of publications, preprints, and posters, see Publications and Presentations.

  • Neural Dynamic Portfolio Control with Provable Learning Guarantees (Submitted)
    with Yizhe Huang, Rui Gao, Shuang Li, Luhao Zhang

    Are there neural approaches to portfolio control that incorporate historical returns with provable end-to-end global guarantees? See more… »

  • Nonsmooth Riemannian Optimization with Inexact Information (In-Preparation)
    with Mateo Díaz and Benjamin Grimmer

    Can nonsmooth convex Riemannian optimization admit nonasymptotic convergence rates using only subgradients, first-order retractions, and vector transports? See more… »

  • Wasserstein Barycenters on Unknown Submanifolds of Wasserstein Space (In-Preparation)
    with Mauro Maggioni

    Given only a local sampler of a non-convex submanifold of Wasserstein space, is there an algorithm to compute the empirical intrinsic mean up to arbitrary accuracy? See more… »

Recent News

Check out news about the latest  Papers ,  Talks ,  Awards , and  More »

Presented Poster at Mathematical Aspects of Data Science Summer School (EFPL)
Sep 1, 2025
Presented Poster at Princeton Machine Learning Theory Summer School
Aug 1, 2025
Convergence Rates for Riemannian Proximal Bundle Methods
Jul 15, 2025
No matching items

More News »

Recent Blog Posts

No matching items

More Posts »

Ian McPherson ©