We study the problem of meta-learning through the lens of online convex optimization,
developing a meta-algorithm bridging the gap between popular gradient-based meta …

We introduce new Perceptron-based algorithms for the online multitask binary classification
problem. Under suitable regularity conditions, our algorithms are shown to improve on their …

State-of-the-art statistical NLP systems for a variety of tasks learn from labeled training data
that is often domain specific. However, there may be multiple domains or sources of interest …

Abstract We propose an Online MultiTask Learning (OMTL) framework which simultaneously
learns the task weight vectors as well as the task relatedness adaptively from the data. Our …

Low-rank tensor learning has many applications in machine learning. A series of batch
learning algorithms have achieved great successes. However, in many emerging …

In this paper we study a class of regularized kernel methods for multi-output learning which
are based on filtering the spectrum of the kernel matrix. The considered methods include …

Personalized activity recognition usually has the problem of highly biased activity patterns
among different tasks/persons. Traditional methods face problems on dealing with those …

This paper addresses the challenge of jointly learning both the per-task model parameters
and the inter-task relationships in a multi-task online learning setting. The proposed …

Better understanding of the potential benefits of information transfer and representation
learning is an important step towards the goal of building intelligent systems that are able to …

In literature, learning with expert advice methods usually assume that a learner always
obtain the true label of every incoming training instance at the end of each trial. However, in …