IEEE Transactions on Pattern Analysis and Machine Intelligence

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is a scholarly archival journal published monthly. This journal covers traditional areas of computer vision and image understanding, all traditional areas of pattern analysis and recognition, and selected areas of machine intelligence. Read the full scope of TPAMI.

Expand your horizons with Colloquium, a monthly survey of abstracts from all CS transactions! Replaces OnlinePlus in January 2017.

From the February 2017 issue

Algorithm-Dependent Generalization Bounds for Multi-Task Learning

By Tongliang Liu, Dacheng Tao, Mingli Song, and Stephen J. Maybank

Often, tasks are collected for multi-task learning (MTL) because they share similar feature structures. Based on this observation, in this paper, we present novel algorithm-dependent generalization bounds for MTL by exploiting the notion of algorithmic stability. We focus on the performance of one particular task and the average performance over multiple tasks by analyzing the generalization ability of a common parameter that is shared in MTL. When focusing on one particular task, with the help of a mild assumption on the feature structures, we interpret the function of the other tasks as a regularizer that produces a specific inductive bias. The algorithm for learning the common parameter, as well as the predictor, is thereby uniformly stable with respect to the domain of the particular task and has a generalization bound with a fast convergence rate of order $\mathcal {O}(1/n)$, where $n$ is the sample size of the particular task. When focusing on the average performance over multiple tasks, we prove that a similar inductive bias exists under certain conditions on the feature structures. Thus, the corresponding algorithm for learning the common parameter is also uniformly stable with respect to the domains of the multiple tasks, and its generalization bound is of the order $\mathcal {O}(1/T)$ , where $T$ is the number of tasks. These theoretical analyses naturally show that the similarity of feature structures in MTL will lead to specific regularizations for predicting, which enables the learning algorithms to generalize fast and correctly from a few examples.

download PDF View the PDF of this article      csdl View this issue in the digital library

Editorials and Announcements


  • We are pleased to announce that Sven Dickinson, a professor in the Department of Computer Science at the University of Toronto, Canada, has been named the new Editor-in-Chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence starting in 2017.
  • According to Thomson Reuters' 2013 Journal Citation Report, TPAMI has an impact factor of 5.694.
  • Get Your Journals as eBooks for Free
  • TPAMI Essential Set now available


Guest Editorials

Reviewers List

Annual Index

Access recently published TPAMI articles

RSSSubscribe to the RSS feed of latest TPAMI content added to the digital library

Mail Sign up for the Transactions Connection newsletter.