dmt

Diego
Martinez Taboada

I spend my time thinking about

  • statistics
  • AI
  • probability
Google Scholar LinkedIn Email
Diego Martinez Taboada
Pittsburgh, Pennsylvania

About me

I'm a PhD student in Statistics and Data Science at Carnegie Mellon University, advised by Aaditya Ramdas.

Previously, I got to learn about mathematics and statistics at the University of Oxford, Sorbonne Université, and Universidade de Santiago de Compostela.

I have also done internships on cool machine learning projects at GResearch and CiTIUS.

Research

Statistics

Sequential decision-making, causal inference, and multiple testing. Learning from streams of data and working with dependent evidence.

Artificial intelligence

The mathematical foundations of modern deep learning. Understanding the behavior of neural networks, their gradients, and their initialization.

Probability

High-dimensional concentration in Hilbert and Banach spaces. Random functions, embeddings, matrices, and operators that need not commute.

  1. 2026Draft

    Gaussian-efficient testing by betting on the mean of bounded data

    Diego Martinez-Taboada, Aaditya Ramdas

    arXiv Code
  2. 2026Under review

    Bentkus-type asymptotic e-values

    Diego Martinez-Taboada, Ben Chugg, Aaditya Ramdas

    arXiv Code
  3. 2026Under review

    Intrinsic-dimension empirical Bernstein inequalities for bounded self-adjoint operators

    Diego Martinez-Taboada, Aaditya Ramdas

    arXiv Code
  4. 2026Under review

    Intrinsic dimension concentration inequalities for self-adjoint operators

    Diego Martinez-Taboada, Aaditya Ramdas

    arXiv

Publications

Google Scholar
  1. 2026

    Sharp empirical Bernstein bounds for the variance of bounded random variables

    Diego Martinez-Taboada, Aaditya Ramdas

    International Conference on Machine Learning (ICML)

    arXiv Code
  2. 2026

    Nonasymptotic heavy-tailed mean estimation in smooth Banach spaces

    Justin Whitehouse, Ben Chugg, Diego Martinez-Taboada, Aaditya Ramdas

    Stochastic Processes and their Applications

    arXiv Journal
  3. 2026

    Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity

    Diego Martinez-Taboada, Tomas Gonzalez-Lara, Aaditya Ramdas

    International Conference on Algorithmic Learning Theory (ALT)

    arXiv Proceedings Code
  4. 2026

    Empirical Bernstein in smooth Banach spaces

    Diego Martinez-Taboada, Aaditya Ramdas

    Annals of Applied Probability

    arXiv Journal
  5. 2025

    Sequential Kernelized Stein Discrepancy

    Diego Martinez-Taboada, Aaditya Ramdas

    International Conference on Artificial Intelligence and Statistics (AISTATS)

    arXiv Proceedings Code
  6. 2024

    Counterfactual Density Estimation using Kernel Stein Discrepancies

    Diego Martinez-Taboada, Edward H. Kennedy

    International Conference on Learning Representations (ICLR)

    arXiv Proceedings
  7. 2023

    An Efficient Doubly-Robust Test for the Kernel Treatment Effect

    Diego Martinez-Taboada, Aaditya Ramdas, Edward H. Kennedy

    Neural Information Processing Systems (NeurIPS)

    arXiv Proceedings

Research notes

Notes I've written with help from my generative friends, revisiting topics from the original papers and explaining them differently to help things click.

New notes will appear here.

Coming soon

Background

  1. 2022 — presentPittsburgh, USA

    Carnegie Mellon University

    PhD in Statistics and Data Science

  2. 2021 — 2022Oxford, UK

    University of Oxford

    MSc in Statistical Science

  3. 2017 — 2021Santiago de Compostela, Spain

    University of Santiago de Compostela

    BSc in Mathematics

    2020 — 2021Paris, France

    Sorbonne Université

    One-year Erasmus exchange

Get in touch

Department of Statistics and Data Science
Carnegie Mellon University · Pittsburgh, PA