Fetching the paper…
Reading the bibliography…
A key problem in the theory of meta-learning is to understand how the task distributions influence transfer risk, the expected error of a meta-learner on a new task drawn from the unknown task distribution.
Maximum likelihood from incomplete data via the em algorithm
Dempster, A. P., Laird, N. M., and Rubin, D. B · 1977
Earlier work this paper cites.
Estimation des densités: risque minimax
Bretagnolle, J. and Huber, C · 1979
Earlier work this paper cites.
Theoretical models of learning to learn
Baxter, J · 1998
Earlier work this paper cites.
A model of inductive bias learning
Baxter, J · 2000
Earlier work this paper cites.
Algorithmic stability and meta-learning
Maurer, A · 2005
Earlier work this paper cites.
Cross-domain video concept detection using adaptive svms
Yang, J., Yan, R., and Hauptmann, A. G · 2007
Earlier work this paper cites.
Transfer bounds for linear feature learning
Maurer, A · 2009
Earlier work this paper cites.
Stability and Hypothesis Transfer Learning
Kuzborskij, I. and Orabona, F · 2013
Cited alongside, same era.
A pac-bayesian bound for lifelong learning
Pentina, A. and Lampert, C · 2014
Cited alongside, same era.
Fast Rates by Transferring from Auxiliary Hypotheses
Kuzborskij, I. and Orabona, F · 2016
Cited alongside, same era.
The benefit of multitask representation learning
Maurer, A., Pontil, M., and Romera-Paredes, B · 2016
Cited alongside, same era.
UCI machine learning repository, 2017
Dua, D. and Graff, C · 2017
Cited alongside, same era.
Model-agnostic meta-learning for fast adaptation of deep networks
Finn, C., Abbeel, P., and Levine, S · 2017
Cited alongside, same era.
Learning to learn around a common mean
Bandit algorithms
Lattimore, T. and Szepesvári, C · 2018
Later among the works it cites.
Learning-to-learn stochastic gradient descent with biased regularization
Denevi, G., Ciliberto, C., Grazzi, R., and Pontil, M · 2019
Later among the works it cites.
Online meta-learning
Finn, C., Rajeswaran, A., Kakade, S., and Levine, S · 2019
Later among the works it cites.
Few-shot learning via learning the representation, provably
Du, S. S., Hu, W., Kakade, S. M., Lee, J. D., and Lei, Q · 2020
Closest in time.
Provable meta-learning of linear representations
Tripuraneni, N., Jin, C., and Jordan, M. I · 2020
Closest in time.
Theoretical bounds on estimation error for meta-learning
Lucas, J., Ren, M., Kameni, I., Pitassi, T., and Zemel, R · 2021
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Denevi, G., Ciliberto, C., Stamos, D., and Pontil, M · 2018
Cited alongside, same era.
Provable guarantees for gradient-based meta-learning
Khodak, M., Balcan, M.-F., and Talwalkar, A
Cited in the paper.
Adaptive gradient-based meta-learning methods
Khodak, M., Balcan, M.-F. F., and Talwalkar, A. S
Cited in the paper.
Closest in time.