arXiv research

Small parameterized towers improve multi-task learning efficiency and generalization.

Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not exhibited the same level of success as in other domains, such as computer vision. In…

Multi-task learning uses auxiliary data or knowledge from relevant tasks to facilitate the learning in a new task. Multi-task optimization applies multi-task learning to optimization to study how to effectively and efficiently tackle multiple optimization problems simultaneously. Evolutionary multi-tasking, or multi-fa…

Disentangled representations naturally emerge in multi-task learning.

While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge. Multi-task learning has emerged as a promising approach for sharing structure across multiple tasks…

Survey on multi-task learning for deep neural networks.

Wide neural networks can benefit from multi-task learning in their infinite-width limit.

Deep multi-task learning benefits from low intrinsic dimensionality, leading to better generalization.

Near-optimal rates for multi-task learning with shared representations.

Improves shared encoder representations for better multi-task learning performance.

A new framework integrates classification and regression tasks in multi-task learning.

We study the stability properties of nonlinear multi-task regression in reproducing Hilbert spaces with operator-valued kernels. Such kernels, a.k.a. multi-task kernels, are appropriate for learning prob- lems with nonscalar outputs like multi-task learning and structured out- put prediction. We show that multi-task ke…

SON-GOKU uses graph coloring to improve multi-task learning by partitioning tasks into compatible groups.

New method learns multiple reward functions for complex tasks.

Research explores the trade-off between multi-task learning and multitasking in deep neural networks.

Multi-task learning is a learning paradigm which seeks to improve the generalization performance of a learning task with the help of some other related tasks. In this paper, we propose a regularization formulation for learning the relationships between tasks in multi-task learning. This formulation can be viewed as a n…

Bayesian approach improves network lasso for multi-task learning.

The paper uses random matrix theory for multi-task regression, improving time series forecasting.

Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-task learning, one needs to centralize data from all the tasks to a single machine. However, in many real-world applications, data of differen…

Develops a method for fairness in multi-task learning using Wasserstein barycenters.

Multi-task sparse feature learning aims to improve the generalization performance by exploiting the shared features among tasks. It has been successfully applied to many applications including computer vision and biomedical informatics. Most of the existing multi-task sparse feature learning algorithms are formulated a…

Flexible multi-task learning framework using summary statistics.

This paper investigates multi-task reinforcement learning in non-Markovian decision making, showing benefits in sample efficiency.

Study improves GMM learning performance through multi-task and transfer learning.

This paper reviews dMTL and methods for selecting auxiliary tasks.

This paper proposes a method to reveal task relationships in multi-task learning models using sparse graphs.

Algorithm learns which weights to share in deep multi-task learning.

Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a nove…

Proposes a transductive matrix completion method with calibration for multi-task learning.

Multi-task learning holds the promise of less data, parameters, and time than training of separate models. We propose a method to automatically search over multi-task architectures while taking resource constraints into consideration. We propose a search space that compactly represents different parameter sharing strat…

Multi-task learning is a powerful method for solving multiple correlated tasks simultaneously. However, it is often impossible to find one single solution to optimize all the tasks, since different tasks might conflict with each other. Recently, a novel method is proposed to find one single Pareto optimal solution with…

Study of multi-task semi-supervised learning in high dimensions.

Paper introduces a new model to handle multi-task learning across different input domains.

New method generates continuous Pareto sets for multi-task learning.

Boosts share routing for multi-task learning with flexible sparse connections.

We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of sequence cl…

CMDE uses deep learning to estimate causal effects from complex data.

This work improves trace norm regularization for multi-task learning with limited data.

In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off. A common compromise is to optimize a proxy objective that minimizes a weighted linear combination o…

Framework for multi-task learning with semiparametric models and nuisance parameters.

Enhances load forecasting for multiple entities with dynamic similarities.

Motivated by multi-task machine learning with Banach spaces, we propose the notion of vector-valued reproducing kernel Banach spaces (RKBS). Basic properties of the spaces and the associated reproducing kernels are investigated. We also present feature map constructions and several concrete examples of vector-valued RK…

New bounds for multi-task learning with varying task sizes.

New algorithm improves learning efficiency in multi-task contextual bandits.

Multi-task learning has shown to significantly enhance the performance of multiple related learning tasks in a variety of situations. We present the fused logistic regression, a sparse multi-task learning approach for binary classification. Specifically, we introduce sparsity inducing penalties over parameter differenc…

Study multi-task learning with low-rank representation in stochastic linear bandits.

Paper tackles multi-task learning for molecular property prediction with limited data.

Multi-task Inverse Reinforcement Learning (IRL) is the problem of inferring multiple reward functions from expert demonstrations. Prior work, built on Bayesian IRL, is unable to scale to complex environments due to computational constraints. This paper contributes a formulation of multi-task IRL in the more computation…