Ari Karchmer

According to our database, Ari Karchmer authored at least 10 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Efficiently Verifiable Proofs of Data Attribution.

Ari Karchmer, Martin Pawelczyk, Seth Neel

CoRR, August, 2025

The Power of Random Features and the Limits of Distribution-Free Gradient Descent.

Ari Karchmer, Eran Malach

CoRR, May, 2025

2024

Distributional PAC-Learning from Nisan's Natural Proofs.

Ari Karchmer

Proceedings of the 15th Innovations in Theoretical Computer Science Conference, 2024

On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning.

Ari Karchmer

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Agnostic Membership Query Learning with Nontrivial Savings: New Results and Techniques.

Ari Karchmer

Proceedings of the International Conference on Algorithmic Learning Theory, 2024

2023

Average-Case PAC-Learning from Nisan's Natural Proofs.

Ari Karchmer

Electron. Colloquium Comput. Complex., 2023

Agnostic Membership Query Learning with Nontrivial Savings: New Results, Techniques.

Ari Karchmer

CoRR, 2023

Theoretical Limits of Provable Security Against Model Extraction by Efficient Observational Defenses.

Ari Karchmer

Proceedings of the 2023 IEEE Conference on Secure and Trustworthy Machine Learning, 2023

2022

The Limits of Provable Security Against Model Extraction.

Ari Karchmer

IACR Cryptol. ePrint Arch., 2022

2021

Covert Learning: How to Learn with an Untrusted Intermediary.

Ran Canetti, Ari Karchmer

IACR Cryptol. ePrint Arch., 2021