AK

- github - google scholar - follow me on X!

I'm a postdoc at Harvard University, where I participate in the SAFR AI lab led by Seth Neel and Salil Vadhan. I obtained my Ph.D. from Boston University under the supervision of Ran Canetti in spring of 2024.

I'm interested in machine learning, AI, and theoretical computer science.

I want to help develop the theory of how machine learning really works—can we predict how ML models will perform/act, before we train (or otherwise do surgery on) them? For instance, some of my recent work contributes to a better understanding when and why multimodal data is useful for ML.

I am now also working on applied research in ML/AI interpretability, such as methods for data attribution and mechanistic interpretability and model editing.

My Ph.D. thesis was in the area of meta-complexity, and in particular, discovered new relationships between the complexity theory of circuit lower bounds and computational learning theory.

blog >>>

berkeley cafe museum >>>





Piet Mondrian, The Red Tree, 1908












Coming soon!

  1. The Power of Random Features Given a Prior.
    Ari Karchmer and Eran Malach.

  2. Better Counterfactual Prediction with Submodular Quadratic Component Models. ATTRIB 2024 workshop @ Neurips 2024.
    Ari Karchmer, Harshay Shah, Andrew Ilyas and Seth Neel.

Refereed Publications

(ab) indicates author names are listed alphabetically.

  1. On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning. ICML 2024.
    Ari Karchmer.
    "Spotlight" paper (3.5% acceptance rate). ArXiv preprint.

  2. Agnostic Membership Query Learning with Nontrivial Savings: New Results and Techniques. ALT 2024.
    Ari Karchmer.
    ArXiv preprint.

  3. Distributional PAC-Learning from Nisan's Natural Proofs. ITCS 2024.
    Ari Karchmer.
    Winner of best student paper award. Invited for publication at TheoretiCS. ArXiv preprint.

  4. Theoretical Limits of Provable Security Against Model Extraction by Efficient Observational Defenses. SaTML 2023.
    Ari Karchmer.
    IACR ePrint.

  5. Covert Learning: How to Learn with an Untrusted Intermediary. TCC 2021. (ab)
    Ran Canetti and Ari Karchmer.
    Invited to Journal of Cryptology. IACR ePrint.


Select Talks

  • "Undetectable Model Stealing with Covert Learning" - Harvard University SAFR AI Lab, Cambridge MA, April '24 Slides
  • "Cryptography and Complexity Theory in the Design and Analysis of ML" - Vector Institue, Toronto CA, April '24 Slides
  • "Learning from Nisan's Natural Proofs" - MIT CIS Seminar, March '24 Slides
  • "Distributional PAC-learning from Nisan's Natural Proofs" - ITCS, Simons Institute, Jan '24 Video
  • "Undetectable Model Stealing and more with Covert Learning" - Google Research MTV, algorithms seminar, Jan '24 Slides
  • "New Approaches to Heuristic PAC-Learning vs. PRFs" - Lower Bounds, Learning, and Average-case Complexity Workshop at Simons Institute, Feb '23 Simons talk
  • "The Limits of Provable Security Against Model Extraction" - Privacy Preserving Machine Learning Workshop at Crypto, Aug '22 PPML talk
  • "Covert Learning: How to Learn with an Untrusted Intermediary" - Charles River Crypto Day at MIT, Nov '21 Crypto day talk

Teaching Fellowships

  • "Responsible AI, Law, Ethics & Society" with Shlomi Hod et al. in Spring 2022
  • "Network Security" with profs Ran Canetti and Sharon Goldberg in Fall 2019
  • "Algebraic Algorithms" with prof Leonid Levin in Fall 2018



Flag Counter