Distributed Minimum Error Entropy Algorithms
Authors: Xin Guo, Ting Hu, Qiang Wu
JMLR 2020 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we study a reproducing kernel-based distributed MEE algorithm, DMEE, which is designed to work with both fully supervised data and semi-supervised data. ... With fully supervised data, our proved learning rates equal the minimax optimal learning rates of the classical pointwise kernel-based regressions. Under the semi-supervised learning scenarios, we show that DMEE exploits unlabeled data effectively, in the sense that first, under the settings with weak regularity assumptions, additional unlabeled data significantly improves the learning rates of DMEE. ... The theoretical analysis is achieved by distributed U-statistics and error decomposition techniques in integral operators. ... This paper provides three main contributions. First, existing analysis of MEE algorithm in the literature has largely been improved, and extended losslessly to DMEE. Our obtained learning rates coincide with the minimax optimal rates of regularized least squares algorithms for pointwise learning. Second, we prove that unlabeled data can significantly improve learning rates under the setting with weak regularity assumptions. Third, we prove that with sufficient unlabeled data, the restriction on the maximum number of computing nodes that labeled data are distributed to is removed. |
| Researcher Affiliation | Academia | Xin Guo EMAIL Department of Applied Mathematics The Hong Kong Polytechnic University Hong Kong, China, and School of Mathematics and Physics The University of Queensland Brisbane, QLD 4072, Australia Ting Hu EMAIL School of Mathematics and Statistics Wuhan University Wuhan, 430072, China Qiang Wu EMAIL Department of Mathematical Sciences Middle Tennessee State University Murfreesboro, TN 37132, USA |
| Pseudocode | No | The paper describes algorithms and methods (e.g., 'distributed MEE algorithm outputs its predicted function f D,λ as the average of the local output functions') but does not contain a formally structured pseudocode block or algorithm steps. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code, nor does it provide links to any code repositories or supplementary materials for code. |
| Open Datasets | No | The paper is theoretical and discusses 'fully supervised data' and 'semi-supervised data' as conceptual inputs for its algorithms. It does not refer to any specific publicly available datasets used for empirical evaluation. |
| Dataset Splits | No | The paper is theoretical and focuses on mathematical analysis and learning rates. It mentions dividing data into subsets for distributed learning (e.g., 'divides a large data set into several subsets'), but this is a conceptual partitioning for theoretical analysis rather than an experimental dataset split for reproduction. |
| Hardware Specification | No | The paper is theoretical and focuses on the mathematical analysis of distributed minimum error entropy algorithms. It does not describe any experimental hardware used. |
| Software Dependencies | No | The paper is theoretical and focuses on mathematical analysis. It does not mention any specific software or library dependencies with version numbers for experimental reproduction. |
| Experiment Setup | No | The paper is theoretical, providing 'learning rates' and 'theoretical analysis.' It does not describe an experimental setup with hyperparameters or specific training configurations. |