Agnostic Sample Compression Schemes for Regression

Authors: Idan Attias, Steve Hanneke, Aryeh Kontorovich, Menachem Sadigurschi

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We obtain the first positive results for bounded sample compression in the agnostic regression setting with the ℓp loss, where p [1, ]. We construct a generic approximate sample compression scheme for real-valued function classes exhibiting exponential size in the fat-shattering dimension but independent of the sample size. Notably, for linear regression, an approximate compression of size linear in the dimension is constructed. Moreover, for ℓ1 and ℓ losses, we can even exhibit an efficient exact sample compression scheme of size linear in the dimension.
Researcher Affiliation Academia 1Department of Computer Science, Ben-Gurion University, Israel 2Department of Computer Science, Purdue University, USA.
Pseudocode Yes Algorithm 1 Approximate Agnostic Sample Compression for ℓp Regression, p [1, ]
Open Source Code No The paper does not provide any statement or link indicating the availability of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not describe experiments run on specific public datasets with access information.
Dataset Splits No The paper is theoretical and does not describe experimental validation with specific dataset splits.
Hardware Specification No The paper is theoretical and does not mention specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not mention specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe a concrete experimental setup with hyperparameters or training configurations.