A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
This paper reviews dMTL and methods for selecting auxiliary tasks.
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…
Robot learns multiple tasks hierarchically by transferring knowledge.
ST-MAML tackles task ambiguity in meta-learning by encoding tasks with stochastic representations.
New algorithm combines curriculum learning with HER for complex object manipulation tasks.
APT-Gen generates tasks to help RL learn in hard problems.
Meta-learning framework uses task similarity through nonparametric kernel regression.
Paper presents IMRCs for evolving tasks with forward and backward learning.
Deep multitask learning boosts performance by sharing learned structure across related tasks. This paper adapts ideas from deep multitask learning to the setting where only a single task is available. The method is formalized as pseudo-task augmentation, in which models are trained with multiple decoders for each task.…
Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong …
Survey on multi-task learning for deep neural networks.
Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between …
Deep multi-task learning attracts much attention in recent years as it achieves good performance in many applications. Feature learning is important to deep multi-task learning for sharing common information among tasks. In this paper, we propose a Hierarchical Graph Neural Network (HGNN) to learn augmented features fo…
New algorithms improve multi-task learning across different environments.
Optimal task order improves continual learning performance.
Single neural network learns multiple tasks from combined data.
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…
Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL…
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…
Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement…
The paper proposes a learning algorithm that improves adaptability and generalization.
Research explores the trade-off between multi-task learning and multitasking in deep neural networks.
FedGTEA learns new tasks in federated learning with task embeddings and alignment.
Despite recent success of deep network-based Reinforcement Learning (RL), it remains elusive to achieve human-level efficiency in learning novel tasks. While previous efforts attempt to address this challenge using meta-learning strategies, they typically suffer from sampling inefficiency with on-policy RL algorithms o…
New method for learning evolving tasks with performance guarantees.
While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is fixed. Due to such restriction, they learn to equally utilize the meta-knowledge across all the tasks…
A new meta-learning BO approach that bypasses surrogate models and directly learns task utility.
AuxiLearn combines auxiliary tasks into a single loss function.
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…
Small parameterized towers improve multi-task learning efficiency and generalization.
Improves deep learning robustness by considering task and model.
The reinforcement learning community has made great strides in designing algorithms capable of exceeding human performance on specific tasks. These algorithms are mostly trained one task at the time, each new task requiring to train a brand new agent instance. This means the learning algorithm is general, but each solu…
Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge. Here, we propose a new approach to sequential learning which leverages the recent discovery of adversari…
This paper proposes a method to reveal task relationships in multi-task learning models using sparse graphs.
Framework adapts to new tasks based on prior knowledge.
Algorithm learns which weights to share in deep multi-task learning.
This work improves trace norm regularization for multi-task learning with limited data.
We study the average case performance of multi-task Gaussian process (GP) regression as captured in the learning curve, i.e. the average Bayes error for a chosen task versus the total number of examples for all tasks. For GP covariances that are the product of an input-dependent covariance function and a free-form …
Improves shared encoder representations for better multi-task learning performance.
This work improves sample efficiency in meta-learning for nonlinear tasks.
COCOA can learn new tasks without forgetting previously learned ones in a distributed setting.
Meta-learning performance is affected by how task diversity is allocated, not just overall variability.
In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks. We propose a framework for multi-task learn- ing that enables one to selectively share the information across the tasks. We assume that each task parameter vector is a linear combi- nat…
HydaLearn dynamically adjusts task weights for better MTL performance.
Meta-learning is a promising strategy for learning to efficiently learn within new tasks, using data gathered from a distribution of tasks. However, the meta-learning literature thus far has focused on the task segmented setting, where at train-time, offline data is assumed to be split according to the underlying task,…
SON-GOKU uses graph coloring to improve multi-task learning by partitioning tasks into compatible groups.
MT-HAL learns features and task associations for multiple tasks with a shared sparse structure.
RTE enables extrapolation to new tasks by learning task transformations.