Provable guarantees for gradient-based meta-learning
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 …
developing a meta-algorithm bridging the gap between popular gradient-based meta …
[PDF][PDF] Linear algorithms for online multitask classification
G Cavallanti, N Cesa-Bianchi, C Gentile - The Journal of Machine Learning …, 2010 - jmlr.org
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 …
problem. Under suitable regularity conditions, our algorithms are shown to improve on their …
Multi-domain learning by confidence-weighted parameter combination
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 …
that is often domain specific. However, there may be multiple domains or sources of interest …
Online learning of multiple tasks and their relationships
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 …
learns the task weight vectors as well as the task relatedness adaptively from the data. Our …
Accelerated online low rank tensor learning for multivariate spatiotemporal streams
Low-rank tensor learning has many applications in machine learning. A series of batch
learning algorithms have achieved great successes. However, in many emerging …
learning algorithms have achieved great successes. However, in many emerging …
[HTML][HTML] Multi-output learning via spectral filtering
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 …
are based on filtering the spectrum of the kernel matrix. The considered methods include …
Large-scale personalized human activity recognition using online multitask learning
Personalized activity recognition usually has the problem of highly biased activity patterns
among different tasks/persons. Traditional methods face problems on dealing with those …
among different tasks/persons. Traditional methods face problems on dealing with those …
Adaptive smoothed online multi-task learning
K Murugesan, H Liu, J Carbonell… - Advances in Neural …, 2016 - proceedings.neurips.cc
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 …
and the inter-task relationships in a multi-task online learning setting. The proposed …
Lifelong learning with weighted majority votes
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 …
learning is an important step towards the goal of building intelligent systems that are able to …
Online active learning with expert advice
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 …
obtain the true label of every incoming training instance at the end of each trial. However, in …