Fetching the paper…
Reading the bibliography…
We introduce ES-MAML, a new framework for solving the model agnostic meta learning (MAML) problem based on Evolution Strategies (ES).
Structured monte carlo sampling for nonisotropic distributions via determinantal point processes
Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, and Yunhao Tang · 1905
Earlier work this paper cites.
Evolutionary algorithms for reinforcement learning
David Moriarty, Alan Schultz, and John Grefenstette · 1999
Earlier work this paper cites.
Determinantal point processes for machine learning
Alex Kulesza and Ben Taskar · 2012
Earlier work this paper cites.
Sampling from determinantal point processes for scalable manifold learning
Christian Wachinger and Polina Golland · 2015
Earlier work this paper cites.
Convergence analysis of alternating direction method of multipliers for a family of nonconvex problems
Mingyi Hong, Zhi-Quan Luo, and Meisam Razaviyayn · 2016
Earlier work this paper cites.
Unbiased simulation for optimizing stochastic function compositions
Jose Blanchet, Donald Goldfarb, Garud Iyengar, Fengpei Li, and Chaoxu Zhou · 2017
Earlier work this paper cites.
Model-agnostic meta-learning for fast adaptation of deep networks
Chelsea Finn, Pieter Abbeel, and Sergey Levine · 2017
Earlier work this paper cites.
SGDR: stochastic gradient descent with warm restarts
Ilya Loshchilov and Frank Hutter · 2017
Earlier work this paper cites.
Random gradient-free minimization of convex functions
Yurii Nesterov and Vladimir Spokoiny · 2017
Earlier work this paper cites.
Evolution strategies as a scalable alternative to reinforcement learning
Tim Salimans, Jonathan Ho, Xi Chen, Szymon Sidor, and Ilya Sutskever · 2017
Earlier work this paper cites.
Felipe Petroski Such, Vashisht Madhavan, Edoardo Conti, Joel Lehman, Kenneth Stanley, and Jeff Clune · 2017
Cited alongside, same era.
Accelerating stochastic composition optimization
Mengdi Wang, Ji Liu, and Xingyuan Fang · 2017
Cited alongside, same era.
Continuous adaptation via meta-learning in nonstationary and competitive environments
Maruan Al-Shedivat, Trapit Bansal, Yura Burda, Ilya Sutskever, Igor Mordatch, and Pieter Abbeel · 2018
Cited alongside, same era.
Structured evolution with compact architectures for scalable policy optimization
Krzysztof Choromanski, Mark Rowland, Vikas Sindhwani, Richard E. Turner, and Adrian Weller · 2018
Cited alongside, same era.
Meta-learning by the baldwin effect
Chrisantha Fernando, Jakub Sygnowski, Simon Osindero, Jane Wang, Tom Schaul, Denis Teplyashin, Pablo Sprechmann, Alexander Pritzel, and Andrei A. Rusu · 2018
Cited alongside, same era.
How to train your MAML
Antreas Antoniou, Harrison Edwards, and Amos J. Storkey · 2019
Closest in time.
Alpha MAML: adaptive model-agnostic meta-learning
Harkirat Singh Behl, Atilim Günes Baydin, and Philip H. S. Torr · 2019
Closest in time.
From complexity to simplicity: Adaptive es-active subspaces for blackbox optimization
Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, and Yunhao Tang · 2019
Closest in time.
Provably robust blackbox optimization for reinforcement learning
Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Deepali Jain, Yuxiang Yang, Atil Iscen, Jasmine Hsu, and Vikas Sindhwani · 2019
Closest in time.
Evolvability ES: scalable and direct optimization of evolvability
Alexander Gajewski, Jeff Clune, Kenneth O. Stanley, and Joel Lehman · 2019
Closest in time.
Taming MAML: efficient unbiased meta-reinforcement learning
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Meta-learning and universality: Deep representations and gradient descent can approximate any learning algorithm
Chelsea Finn and Sergey Levine · 2018
Cited alongside, same era.
Probabilistic model-agnostic meta-learning
Chelsea Finn, Kelvin Xu, and Sergey Levine · 2018
Cited alongside, same era.
DiCE: The infinitely differentiable Monte Carlo estimator
Jakob Foerster, Gregory Farquhar, Maruan Al-Shedivat, Tim Rocktäschel, Eric Xing, and Shimon Whiteson · 2018
Cited alongside, same era.
Simple random search provides a competitive approach to reinforcement learning
Horia Mania, Aurelia Guy, and Benjamin Recht · 2018
Cited alongside, same era.
Hao Liu, Richard Socher, and Caiming Xiong · 2019
Closest in time.
Deep neuroevolution of recurrent and discrete world models
Sebastian Risi and Kenneth Stanley · 2019
Closest in time.
Promp: Proximal meta-policy search
Jonas Rothfuss, Dennis Lee, Ignasi Clavera, Tamim Asfour, and Pieter Abbeel · 2019
Closest in time.
Norml: No-reward meta learning
Yuxiang Yang, Ken Caluwaerts, Atil Iscen, Jie Tan, and Chelsea Finn · 2019
Closest in time.