On the Learnability of Distribution Classes with Adaptive Adversaries
Authors: Tosca Lechner, Alex Bie, Gautam Kamath
ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We consider the question of learnability of distribution classes in the presence of adaptive adversaries... We formulate a general notion of learnability with respect to adaptive adversaries... We show that learnability... is a strictly stronger condition... The present paper answers this question in the negative. We show that additive corruptions are strictly more powerful in the adaptive model than in the oblivious model. To prove the result, we examine the relationship... This technique, based on a recent result of Ben-David & Lechner (2025), says the following: Theorem 1.2 (Informal version of Theorem 5.2). |
| Researcher Affiliation | Collaboration | 1Vector Institute 2Google 3University of Waterloo. Correspondence to: Tosca Lechner <EMAIL>. |
| Pseudocode | No | The paper describes algorithms conceptually and presents proofs and theoretical constructions, but it does not include any clearly labeled pseudocode blocks or algorithm listings in a structured format. |
| Open Source Code | No | The paper does not contain any statements about releasing code, nor does it provide links to any code repositories. The work is theoretical in nature. |
| Open Datasets | No | The paper is theoretical and focuses on 'distribution classes' (C, Cg) rather than specific named datasets for empirical evaluation. No datasets are mentioned as being used or made publicly available. |
| Dataset Splits | No | The paper is theoretical and does not describe experiments that would involve dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and does not describe any experiments that would require specific hardware, thus no hardware specifications are provided. |
| Software Dependencies | No | The paper is theoretical and does not describe any experiments that would require specific software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and focuses on mathematical proofs and definitions rather than empirical experiments. Therefore, no experimental setup details, hyperparameters, or training configurations are provided. |