BanditMTL: Bandit-based Multi-task Learning for Text Classification
Task variance regularization, which can be used to improve the generalization of Multi-task Learning (MTL) models, remains unexplored in multi-task text classification. Accordingly, to fill this gap, this paper investigates how the task might be effectively regularized, and consequently proposes a multi-task learning method based on adversarial multi-armed bandit. The proposed method, named BanditMTL, regularizes the task variance by means of a mirror gradient ascent-descent algorithm. Adopting BanditMTL in the multi-task text classification context is found to achieve state-of-the-art performance. The results of extensive experiments back up our theoretical analysis and validate the superiority of our proposals.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationMulti-Task Learningtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Nonparametric Stochastic Contextual Bandits
We analyze the $K$-armed bandit problem where the reward for each arm is a noisy realization based on an observed context under mild nonparametric assumptions. We attain tight results for top-arm identification and a sub…
General Classificationimage-classificationImage ClassificationMulti-Armed BanditsAdapting multi-armed bandits policies to contextual bandits scenarios
This work explores adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms such as logistic regression as black-box orac…
Binary ClassificationClassificationGeneral ClassificationMulti-Armed Bandits+2Learning Multiple Tasks in Parallel with a Shared Annotator
We introduce a new multi-task framework, in which $K$ online learners are sharing a single annotator with limited bandwidth. On each round, each of the $K$ learners receives an input, and makes a prediction about the lab…
Binary ClassificationDocument ClassificationGeneral ClassificationMulti-Armed Bandits+2Learning Effective Exploration Strategies For Contextual Bandits
In contextual bandits, an algorithm must choose actions given observed contexts, learning from a reward signal that is observed only for the action chosen. This leads to an exploration/exploitation trade-off: the algorit…
Imitation LearningLearning-To-RankMeta-LearningMulti-Armed BanditsA Classification View on Meta Learning Bandits
Contextual multi-armed bandits are a popular choice to model sequential decision-making. E.g., in a healthcare application we may perform various tests to asses a patient condition (exploration) and then decide on the be…
ClassificationMeta-LearningMulti-Armed BanditsSequential Decision Making