DeepAI AI Chat
Log In Sign Up

Accumulating Knowledge for Lifelong Online Learning

by   Changjian Shui, et al.
Université Laval

Lifelong learning can be viewed as a continuous transfer learning procedure over consecutive tasks, where learning a given task depends on accumulated knowledge --- the so-called knowledge base. Most published work on lifelong learning makes a batch processing of each task, implying that a data collection step is required beforehand. We are proposing a new framework, lifelong online learning, in which the learning procedure for each task is interactive. This is done through a computationally efficient algorithm where the predicted result for a given task is made by combining two intermediate predictions: by using only the information from the current task and by relying on the accumulated knowledge. In this work, two challenges are tackled: making no assumption on the task generation distribution, and processing with a possibly unknown number of instances for each task. We are providing a theoretical analysis of this algorithm, with a cumulative error upper bound for each task. We find that under some mild conditions, the algorithm can still benefit from a small cumulative error even when facing few interactions. Moreover, we provide experimental results on both synthetic and real datasets that validate the correct behavior and practical usefulness of the proposed algorithm.


page 1

page 2

page 3

page 4


Transferred Q-learning

We consider Q-learning with knowledge transfer, using samples from a tar...

Online Learning: A Comprehensive Survey

Online learning represents an important family of machine learning algor...

TopRank+: A Refinement of TopRank Algorithm

Online learning to rank is a core problem in machine learning. In Lattim...

Online learning in MDPs with side information

We study online learning of finite Markov decision process (MDP) problem...

Generalization Properties of Doubly Online Learning Algorithms

Doubly online learning algorithms are scalable kernel methods that perfo...

Identification of AC Networks via Online Learning

The increasing integration of intermittent renewable generation in power...

Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances

In today's digital world, we are confronted with an explosion of data an...