Mitchell Ostrow

Computational Neuroscience PhD Candidate at MIT.

Ostrow_Mitchellheadshot.jpg

I’m a 3rd year PhD student at MIT. I’m interested in bridging systems neuroscience, cognitive science, and deep learning through the lens of dynamical systems theory and machine learning. To that end, I design and use quantitative methods to understand computations performed by both biological and artificial neural networks. I’ve worked in medicine (as an EMT), experimental neuroscience, computational neuroscience, and artificial intelligence (in industry).

I also work as a freelance editor, especially for college admission essays and graduate school statements of purpose, but I can edit both technical and non-technical pieces more generally. Feel free to reach out to me at [last-name] (at) mit.edu if you’re interested.

I’m grateful to have been supported at MIT by the Computationally-Enabled Integrative Neuroscience Fellowship and the Praecis Presidential Fellowship. I’m currently supported by the NSF GRFP.

Simply Neuroscience interviewed me on their podcast, The Synapse, about doing neuroscience research at Yale. Link here.

news

Jul 25, 2025 DSA is featured as a tutorial in the Neuromatch Academy NeuroAI course! Thanks to Alex Murphy and Xaq Pitkow.
Feb 15, 2025 Our submission “AgentDSA: Dynamical Similarity Analysis for Neural Controllers” was accepted to the Reinforcement Learning and Decision Making Conference!
Feb 08, 2025 Very happy to have contributed to the Computation-Thru-Dynamics Benchmark, led by Chris Versteeg! https://www.biorxiv.org/content/10.1101/2025.02.07.637062.abstract
Nov 08, 2024 I’ve successfully passed my qualification exam!
Jun 24, 2024 I’m starting an internship at Meta doing Machine Learning Research on the Neuromotor Interfaces Team in New York City!
Jun 17, 2024 My second paper, “Delay Embedding Theory of Neural Sequence Models”, was accepted to the ICML 2024 Workshop on Next Generation Sequence Models! https://arxiv.org/abs/2406.11993v1
Apr 15, 2024 I’m very fortunate to have won the National Science Foundation’s Graduate Research Fellowship, to fund the next three years of my research!
Jan 24, 2024 My paper, “Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis” was accepted to the Cognitive Computational Neuroscience conference as an oral presentation (4%) and to COSYNE (Computational Systems Neuroscience conference) as an oral, (2%)!
Jun 20, 2023 My first full paper preprint is out! https://arxiv.org/abs/2306.10168, and was accepted to NeurIPS, 2023!
Mar 31, 2023 After four excellent rotations, I am joining Ila Fiete’s lab for my thesis work!
Mar 28, 2023 Our abstract ‘Do Deep Neural Networks Have Concepts?’ was selected as a talk at the Philosophy of Deep Learning Conference, hosted at NYU
Aug 28, 2022 Starting PhD! 👨🏻‍🎓
Dec 18, 2021 Graduated from Yale.

selected publications

  1. jacobian.png
    Characterizing control between interacting subsystems with deep Jacobian estimation
    Adam J. Eisen, Mitchell Ostrow, Sarthak Chandra, and 3 more authors
    arxiv, 2025
  2. horseastronaut.jpg
    How Diffusion Models Learn to Factorize and Compose
    Qiyao Liang, Ziming Liu, Mitchell Ostrow, and 1 more author
    Neural Information Processing Systems, 2024
  3. delayembed.png
    Delay Embedding Theory of Neural Sequence Models
    Mitchell Ostrow, Adam Eisen, and Ila Fiete
    International Conference on Machine Learning (ICML) workshop on Next Generation Sequence Modeling, 2024
  4. lstm.png
    Representational Geometry of Social Inference and Generalization in a Competitive Game
    Mitchell Ostrow, G.R. Yang, and H. Seo
    Robotics: Science and Systems, 2022
  5. torus.jpeg
    Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis
    Mitchell Ostrow, Adam Eisen, Leo Kozachkov, and 1 more author
    Neural Information Processing Systems, 2023