On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms
作者： Asuman Ozdaglar , Aryan Mokhtari , Alireza Fallah
DOI:
关键词: Computer science 、 Symbolic convergence theory 、 Stationary point 、 Norm (mathematics) 、 Algorithm 、 Gradient based algorithm
摘要: … -based Model-Agnostic MetaLearning (MAML) methods and … We start with the MAML method and its firstorder … for the implementation of these algorithms including how to choose their …
arxiv.org
harvard.edu参考文章(31)
Learning to learn Learning to learn. pp. 354- 354 ,(1998) , 10.1007/978-1-4615-5529-2
Santosh S. Vempala, Avrim Blum, Maria-Florina Balcan, Efficient Representations for Lifelong Learning and Autoencoding conference on learning theory. pp. 191- 210 ,(2015)
Yoshua Bengio, Samy Bengio, Jocelyn Cloutier, Jan Gescei, On the Optimization of a Synaptic Learning Rule Routledge. pp. 281- 303 ,(2013) , 10.4324/9780203773833-22
Yoshua Bengio, James Bergstra, Random search for hyper-parameter optimization Journal of Machine Learning Research. ,vol. 13, pp. 281- 305 ,(2012)
Yoshua Bengio, Rémi Bardenet, James S. Bergstra, Balázs Kégl, Algorithms for Hyper-Parameter Optimization neural information processing systems. ,vol. 24, pp. 2546- 2554 ,(2011)
Jonathan Baxter, A model of inductive bias learning Journal of Artificial Intelligence Research. ,vol. 12, pp. 149- 198 ,(2000) , 10.1613/JAIR.731
David A. Wooff, Bounds on Reciprocal Moments with Applications and Developments in Stein Estimation and Post‐Stratification Journal of the royal statistical society series b-methodological. ,vol. 47, pp. 362- 371 ,(1985) , 10.1111/J.2517-6161.1985.TB01365.X
Nikhil Naik, Otkrist Gupta, Ramesh Raskar, Bowen Baker, Designing Neural Network Architectures using Reinforcement Learning international conference on learning representations. ,(2016)
Pieter Abbeel, Chelsea Finn, Sergey Levine, Model-agnostic meta-learning for fast adaptation of deep networks international conference on machine learning. pp. 1126- 1135 ,(2017)
Hang Li, Zhenguo Li, Fei Chen, Fengwei Zhou, Meta-SGD: Learning to Learn Quickly for Few Shot Learning. arXiv: Learning. ,(2017)