paper-with-me

Papers

Dif-MAML: Decentralized Multi-Agent Meta-Learning

2020-10-06 · Mert Kayaalp, Stefan Vlaski, Ali H. Sayed

The objective of meta-learning is to exploit the knowledge obtained from observed tasks to improve adaptation to unseen tasks. As such, meta-learners are able to generalize better when they are trained with a larger number of observed tasks and with a larger amount of data per task. Given the amount of resources that are needed, it is generally difficult to expect the tasks, their respective data, and the necessary computational capacity to be available at a single central location. It is more natural to encounter situations where these resources are spread across several agents connected by some graph topology. The formalism of meta-learning is actually well-suited to this decentralized setting, where the learner would be able to benefit from information and computational power spread across the agents. Motivated by this observation, in this work, we propose a cooperative fully-decentralized multi-agent meta-learning algorithm, referred to as Diffusion-based MAML or Dif-MAML. Decentralized optimization algorithms are superior to centralized implementations in terms of scalability, avoidance of communication bottlenecks, and privacy guarantees. The work provides a detailed theoretical analysis to show that the proposed strategy allows a collection of agents to attain agreement at a linear rate and to converge to a stationary point of the aggregate MAML objective even in non-convex environments. Simulation results illustrate the theoretical findings and the superior performance relative to the traditional non-cooperative setting.

📄 PDF Abstract BibTeX arXiv:2010.02870

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-Learning

Methods 이 논문이 사용한 방법론

MAML 설명 없음

Similar Papers 제목 키워드 기반

Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning

2020-12-01 · NeurIPS 2020 12 · Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin 외

Continual learning agents experience a stream of (related) tasks. The main challenge is that the agent must not forget previous tasks and also adapt to novel tasks in the stream. We are interested in the intersection of …

Continual LearningMeta-Learning

Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning

2020-03-12 · NeurIPS 2020 12 · Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin 외

Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continu…

Continual LearningMeta-Learning

NoRML: No-Reward Meta Learning

2019-03-04 · Yuxiang Yang, Ken Caluwaerts, Atil Iscen, Jie Tan 외

Efficiently adapting to new environments and changes in dynamics is critical for agents to successfully operate in the real world. Reinforcement learning (RL) based approaches typically rely on external reward feedback f…

Meta-LearningReinforcement LearningReinforcement Learning (RL)

Recasting Gradient-Based Meta-Learning as Hierarchical Bayes

2018-01-26 · ICLR 2018 1 · Erin Grant, Chelsea Finn, Sergey Levine, Trevor Darrell 외

Meta-learning allows an intelligent agent to leverage prior learning episodes as a basis for quickly improving performance on a novel task. Bayesian hierarchical modeling provides a theoretical framework for formalizing …

Meta-Learning

Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?

2022-03-06 · Lisha Chen, Tianyi Chen

Meta learning aims at learning a model that can quickly adapt to unseen tasks. Widely used meta learning methods include model agnostic meta learning (MAML), implicit MAML, Bayesian MAML. Thanks to its ability of modelin…

Meta-Learningmodel