Multi-Task Learning and Algorithmic Stability

Authors: Yu Zhang

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we study multi-task algorithms from the perspective of the algorithmic stability. We give a definition of the multi-task uniform stability, a generalization of the conventional uniform stability, which measures the maximum difference between the loss of a multi-task algorithm trained on a data set and that of the multitask algorithm trained on the same data set but with a data point removed in each task. In order to analyze multi-task algorithms based on multi-task uniform stability, we prove a generalized Mc Diarmid s inequality which assumes the difference bound condition holds by changing multiple input arguments instead of only one in the conventional Mc Diarmid s inequality. By using the generalized Mc Diarmid s inequality as a tool, we can analyze the generalization performance of general multitask algorithms in terms of the multi-task uniform stability. Moreover, as applications, we prove generalization bounds of several representative regularized multi-task algorithms.
Researcher Affiliation Academia Yu Zhang Department of Computer Science, Hong Kong Baptist University The Institute of Research and Continuing Education, Hong Kong Baptist University (Shenzhen)
Pseudocode No The paper contains mathematical definitions, theorems, and proofs, but no pseudocode or algorithm blocks.
Open Source Code No The paper does not mention releasing any open-source code.
Open Datasets No The paper is theoretical and does not describe or use specific datasets for training.
Dataset Splits No The paper is theoretical and does not describe dataset splits for validation.
Hardware Specification No The paper is theoretical and does not describe the hardware used for any experiments.
Software Dependencies No The paper is theoretical and does not mention any software dependencies with specific version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training settings.