Generation from Noisy Examples
Authors: Ananth Raman, Vinod Raman
ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We continue to study the learning-theoretic foundations of generation by extending the results from Kleinberg & Mullainathan (2024) and Li et al. (2024) to account for noisy example streams. In this paper, we provide necessary and sufficient conditions for when a binary hypothesis class can be noisily generatable. We provide such conditions with respect to various constraints on the number of distinct examples that need to be seen before perfect generation of positive examples. Interestingly, for finite and countable classes we show that generatability is largely unaffected by the presence of a finite number of noisy examples. |
| Researcher Affiliation | Academia | Ananth Raman * 1 Vinod Raman * 2 *Equal contribution 1Bridgewater-Raritan Regional High School 2University of Michigan, Ann Arbor. Correspondence to: Vinod Raman <EMAIL>. |
| Pseudocode | Yes | Algorithm 1 Generator G Input: Hypothesis class H and non-uniform generator Q |
| Open Source Code | No | The paper does not provide any specific links to source code repositories, nor does it state that code is available in supplementary materials or upon request. There is no mention of releasing the code. |
| Open Datasets | No | The paper focuses on theoretical contributions to the foundations of generation. It does not conduct experiments on any specific datasets, therefore no concrete access information for open datasets is provided. |
| Dataset Splits | No | The paper presents theoretical research and does not describe any empirical experiments involving data. Therefore, there is no mention of dataset splits like training, validation, or test sets. |
| Hardware Specification | No | The paper is theoretical in nature and does not report on any experimental results that would require specific hardware. No hardware specifications are mentioned. |
| Software Dependencies | No | The paper focuses on theoretical concepts and proofs. It does not describe any implementation details or experiments that would require specific software libraries or tools with version numbers. |
| Experiment Setup | No | The paper is theoretical and does not present experimental results. Therefore, there are no details regarding experimental setup, hyperparameters, or training configurations. |