Hard-Margin Active Linear Regression

Authors: Elad Hazan, Zohar Karnin

ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We consider the fundamental problem of linear regression in which the designer can actively choose observations. This model naturally captures various experiment design settings in medical experiments, ad placement problems and more. Whereas previous literature addresses the soft-margin or mean-square-error variants of the problem, we consider a natural machine learning hard-margin criterion. In this setting, we show that active learning admits significantly better sample complexity bounds than the passive learning counterpart, and give efficient algorithms that attain near-optimal bounds.
Researcher Affiliation Collaboration Elad Hazan EHAZAN@IE.TECHNION.AC.IL Technion, Haifa, Israel Zohar Karnin ZKARNIN@YAHOO.COM Yahoo Labs, Haifa, Israel
Pseudocode Yes Algorithm 1 Sample(K) ... Algorithm 2 Primal-Dual Algorithm ... Algorithm 3 Verification
Open Source Code No The paper does not provide any statements about releasing code or links to a code repository.
Open Datasets No This paper is theoretical and focuses on algorithm design and complexity bounds. It does not describe experiments performed on specific publicly available datasets for training. It defines a set of data points K = {x1, ..., xn} for theoretical analysis, but this is not a real-world dataset.
Dataset Splits No This paper is theoretical and focuses on algorithm design and complexity bounds. It does not describe empirical experiments with dataset splits (training, validation, test). While it describes a "Validation" procedure (Algorithm 3), this refers to verifying a hypothesis, not splitting a dataset for empirical validation.
Hardware Specification No This paper is theoretical and does not describe any specific hardware used for running experiments.
Software Dependencies No This paper is theoretical and does not list any specific software dependencies with version numbers.
Experiment Setup No This paper is theoretical and focuses on algorithm design and complexity bounds. It does not include specific details about experimental setup, hyperparameters, or system-level training settings.