Semi-supervised Active Linear Regression

Authors: Nived Rajaraman, Fnu Devvrit, Pranjal Awasthi

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we introduce an instance dependent parameter called the reduced rank, denoted RX, and propose an efficient algorithm with query complexity O(RX/ϵ). This result directly implies improved upper bounds for two important special cases: (i) active ridge regression, and (ii) active kernel ridge regression... Finally, we introduce a distributional version of the problem... here, for every X, we prove a matching instancewise lower bound of Ω(RX/ϵ) on the query complexity of any algorithm.
Researcher Affiliation Collaboration Fnu Devvrit Department of Computer Science University of Texas at Austin devvrit@cs.utexas.edu Nived Rajaraman Department of Electrical Engineering and Computer Sciences University of California, Berkeley nived.rajaraman@berkeley.edu Pranjal Awasthi Google Research & Department of Computer Science Rutgers University pranjal.awasthi@rutgers.edu
Pseudocode Yes Algorithm 1: ASURA (Active semi-SUpervised Regression Algorithm)... Algorithm 2: ϵ-well balanced sampling procedure for SSAR
Open Source Code No The paper is theoretical and does not mention the release of open-source code for the described methodology, nor does it provide any links to a code repository.
Open Datasets No The paper focuses on theoretical analysis and algorithm design and does not describe experiments performed on specific publicly available datasets or provide access information for any dataset.
Dataset Splits No The paper does not conduct empirical studies, therefore, there is no mention of training, validation, or test dataset splits.
Hardware Specification No The paper is theoretical and does not report on experiments, therefore, no specific hardware specifications are mentioned.
Software Dependencies No The paper focuses on theoretical contributions and does not specify software dependencies with version numbers required for reproducing experimental results.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details, hyperparameters, or training configurations.