The information-theoretic value of unlabeled data in semi-supervised learning

Authors: Alexander Golovnev, David Pal, Balazs Szorenyi

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical More specifically, we prove a separation by Θ(log n) multiplicative factor for the class of projections over the Boolean hypercube of dimension n. We prove that there is no separation for the class of all functions on domain of any size.
Researcher Affiliation Collaboration 1Harvard University, Cambridge, MA, USA 2Yahoo Research, New York, NY, USA.
Pseudocode No The paper focuses on mathematical proofs and theoretical derivations and does not include any pseudocode or algorithm blocks.
Open Source Code No The paper is theoretical and focuses on proofs and bounds; it does not describe any specific software implementation and therefore does not provide open-source code.
Open Datasets No This theoretical paper does not involve empirical training with datasets.
Dataset Splits No This theoretical paper does not involve empirical validation with datasets.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require hardware specifications.
Software Dependencies No The paper is theoretical and does not detail any software dependencies with version numbers for experimental reproducibility.
Experiment Setup No The paper is theoretical and does not include details about an experimental setup, such as hyperparameters or training configurations.