Bayesian Model-Agnostic Meta-Learning

Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines scalable gradient-based meta-learning with nonparametric variational inference in a principled probabilistic framework. During fast adaptation, the method is capable of learning complex uncertainty structure beyond a point estimate or a simple Gaussian approximation. In addition, a robust Bayesian meta-update mechanism with a new meta-loss prevents overfitting during meta-update. Remaining an efficient gradient-based meta-learner, the method is also model-agnostic and simple to implement. Experiment results show the accuracy and robustness of the proposed method in various tasks: sinusoidal regression, image classification, active learning, and reinforcement learning.

[1]  J. Biggs.  THE ROLE OF METALEARNING IN STUDY PROCESSES , 1985 .

[2]  L. L. Cam,et al.  Asymptotic Methods In Statistical Decision Theory , 1986 .

[3]  Linda B. Smith,et al.  The importance of shape in early lexical learning , 1988 .

[4]  J. Tenenbaum.  A Bayesian framework for concept learning , 1999 .

[5]  Pietro Perona,et al.  A Bayesian approach to unsupervised one-shot learning of object categories , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[7]  Neil D. Lawrence,et al.  Learning to learn with the informative vector machine , 2004, ICML.

[8]  Hans-Peter Kriegel,et al.  Integrating structured biological data by Kernel Maximum Mean Discrepancy , 2006, ISMB.

[9]  Hal Daumé,et al.  Bayesian Multitask Learning with Latent Hierarchies , 2009, UAI.

[10]  Radford M. Neal.  MCMC Using Hamiltonian Dynamics , 2011, 1206.1901.

[11]  Yee Whye Teh,et al.  Bayesian Learning via Stochastic Gradient Langevin Dynamics , 2011, ICML.

[12]  Ahn,et al.  Bayesian posterior sampling via stochastic gradient Fisher scoring Bayesian Posterior Sampling via Stochastic Gradient Fisher Scoring , 2012 .

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  Yuval Tassa,et al.  MuJoCo: A physics engine for model-based control , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Sergey Levine,et al.  Trust Region Policy Optimization , 2015, ICML.

[16]  Vivek Rathod,et al.  Bayesian dark knowledge , 2015, NIPS.

[17]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Roger B. Grosse,et al.  Optimizing Neural Networks with Kronecker-factored Approximate Curvature , 2015, ICML.

[20]  Filip De Turck,et al.  VIME: Variational Information Maximizing Exploration , 2016, NIPS.

[21]  Daan Wierstra,et al.  Meta-Learning with Memory-Augmented Neural Networks , 2016, ICML.

[22]  Dilin Wang,et al.  Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm , 2016, NIPS.

[23]  Peter L. Bartlett,et al.  RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning , 2016, ArXiv.

[24]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[25]  Pieter Abbeel,et al.  Meta-Learning with Temporal Convolutions , 2017, ArXiv.

[26]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[27]  Yang Liu,et al.  Stein Variational Policy Gradient , 2017, UAI.

[28]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[29]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[30]  Zoubin Ghahramani,et al.  Deep Bayesian Active Learning with Image Data , 2017, ICML.

[31]  Linda B. Smith,et al.  A Developmental Approach to Machine Learning? , 2017, Front. Psychol..

[32]  Bernhard Schölkopf,et al.  Discriminative k-shot learning using probabilistic models , 2017, ArXiv.

[33]  Thomas L. Griffiths,et al.  Recasting Gradient-Based Meta-Learning as Hierarchical Bayes , 2018, ICLR.

[34]  Joshua Achiam,et al.  On First-Order Meta-Learning Algorithms , 2018, ArXiv.