Fetching the paper…
Reading the bibliography…
Although model-agnostic meta-learning (MAML) is a very successful algorithm in meta-learning practice, it can have high computational cost because it updates all model parameters over both the inner loop of task-specific adaptation and the outer-loop of meta initialization training.
On the convergence theory of gradient-based model-agnostic meta-learning algorithms
Fallah, A · 1908
Earlier work this paper cites.
History-gradient aided batch size adaptation for variance reduced algorithms
Ji, K · 1910
Earlier work this paper cites.
Learning a synaptic learning rule
Bengio, Y · 1991
Earlier work this paper cites.
Multi-step model-agnostic meta-learning: Convergence and improved algorithms
Ji, K · 2002
Earlier work this paper cites.
Near-optimal algorithms for minimax optimization
Lin, T · 2002
Earlier work this paper cites.
Learning multiple layers of features from tiny images
Krizhevsky, A · 2009
Earlier work this paper cites.
Learning to learn
Thrun, S · 2012
Earlier work this paper cites.
Stochastic first-and zeroth-order methods for nonconvex stochastic programming
Ghadimi, S · 2013
Earlier work this paper cites.
Adam: A method for stochastic optimization
Kingma, D. P · 2014
Earlier work this paper cites.
Siamese neural networks for one-shot image recognition
Koch, G · 2015
Earlier work this paper cites.
Imagenet large scale visual recognition challenge
Russakovsky, O · 2015
Earlier work this paper cites.
Optimization as a model for few-shot learning
Ravi, S · 2016
Cited alongside, same era.
Matching networks for one shot learning
Vinyals, O · 2016
Cited alongside, same era.
Meta-learning and universality: Deep representations and gradient descent can approximate any learning algorithm
Finn, C · 2017
Cited alongside, same era.
Meta networks
Munkhdalai, T · 2017
Cited alongside, same era.
Prototypical networks for few-shot learning
Snell, J · 2017
Cited alongside, same era.
Meta-learning with differentiable closed-form solvers
Bertinetto, L · 2018
Cited alongside, same era.
Probabilistic model-agnostic meta-learning
Tadam: Task dependent adaptive metric for improved few-shot learning
Oreshkin, B · 2018
Later among the works it cites.
SpiderBoost: A class of faster variance-reduced algorithms for nonconvex optimization
Wang, Z · 2018
Later among the works it cites.
Deep meta-learning: Learning to learn in the concept space
Zhou, F · 2018
Later among the works it cites.
learn2learn
Arnold, S. M · 2019
Later among the works it cites.
Online meta-learning
Finn, C · 2019
Later among the works it cites.
Meta-learning with differentiable convex optimization
Lee, K · 2019
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Finn, C · 2018
Cited alongside, same era.
Approximation methods for bilevel programming
Ghadimi, S · 2018
Cited alongside, same era.
Online gradient-based mixtures for transfer modulation in meta-learning
Jerfel, G · 2018
Cited alongside, same era.
Reptile: a scalable metalearning algorithm
Nichol, A · 2018
Cited alongside, same era.
Model-agnostic meta-learning for fast adaptation of deep networks
Finn, C
Cited in the paper.
One-shot visual imitation learning via meta-learning
Finn, C
Cited in the paper.
Meta-learning for low-resource natural language generation in task-oriented dialogue systems
Mi, F · 2019
Later among the works it cites.
Rapid learning or feature reuse? towards understanding the effectiveness of MAML
Raghu, A · 2019
Later among the works it cites.
Meta-learning with implicit gradients
Rajeswaran, A · 2019
Later among the works it cites.
Efficient meta learning via minibatch proximal update
Zhou, P · 2019
Later among the works it cites.