Certain and Approximately Certain Models for Statistical Learning
This addresses the time-consuming data imputation problem for users handling incomplete real-world datasets in machine learning, though it appears incremental as it builds on existing paradigms.
The paper tackles the problem of learning accurate models directly from data with missing values, showing that imputation is unnecessary for certain training data and target models, and their algorithms significantly reduce imputation time and effort without high computational overhead.
Real-world data is often incomplete and contains missing values. To train accurate models over real-world datasets, users need to spend a substantial amount of time and resources imputing and finding proper values for missing data items. In this paper, we demonstrate that it is possible to learn accurate models directly from data with missing values for certain training data and target models. We propose a unified approach for checking the necessity of data imputation to learn accurate models across various widely-used machine learning paradigms. We build efficient algorithms with theoretical guarantees to check this necessity and return accurate models in cases where imputation is unnecessary. Our extensive experiments indicate that our proposed algorithms significantly reduce the amount of time and effort needed for data imputation without imposing considerable computational overhead.