arXiv research

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

Contextual bandits are a form of multi-armed bandit in which the agent has access to predictive side information (known as the context) for each arm at each time step, and have been used to model personalized news recommendation, ad placement, and other applications. In this work, we propose a multi-task learning frame…

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

A TS algorithm improves performance in multi-task bandits with transfer.

New algorithms minimize regret in multi-task and lifelong linear bandits with shared representation.

New algorithms improve multi-task bandit performance by transferring reward samples.

New algorithm reduces sample complexity for multi-task bandits.

Cellular network configuration plays a critical role in network performance. In current practice, network configuration depends heavily on field experience of engineers and often remains static for a long period of time. This practice is far from optimal. To address this limitation, online-learning-based approaches hav…

The paper tackles budget allocation for multiple campaigns using a novel combinatorial bandit approach.

The paper tackles decision making problems with funnel structure in email marketing campaigns.

We discuss multi-task online learning when a decision maker has to deal simultaneously with M tasks. The tasks are related, which is modeled by imposing that the M-tuple of actions taken by the decision maker needs to satisfy certain constraints. We give natural examples of such restrictions and then discuss a general …

MixTS uses a mixture prior to analyze Thompson Sampling in multi-task learning.

Algorithm finds latent structure in value functions for improved reinforcement learning.

Efficiently identifies best algorithms for game tasks.

Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a simulation environment to the real world. Several existing approaches involve sampling large batches of traj…

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

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…

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

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…

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 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…

Disentangled representations naturally emerge in multi-task learning.

Multi-task learning (MTL) has achieved success over a wide range of problems, where the goal is to improve the performance of a primary task using a set of relevant auxiliary tasks. However, when the usefulness of the auxiliary tasks w.r.t. the primary task is not known a priori, the success of MTL models depends on th…

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…

New method learns multiple reward functions for complex tasks.

MUMBO optimizes multiple tasks efficiently, even with low-cost related functions.

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

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

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.

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

Paper estimates noise covariance in correlated multi-task linear models.

Develops a scalable multi-task Gaussian process with neural embedding for improved performance.

Survey on multi-task learning for deep neural networks.

Bayesian approach improves network lasso for multi-task learning.

Adaptive data fusion boosts efficiency in multi-task optimization.

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…

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

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

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

Flexible multi-task learning framework using summary statistics.

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…

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…

Paper extends multi-task Gaussian Cox processes for heterogeneous tasks.

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

New method uses shared attention for multi-task time series forecasting.

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