Corpus ID: 221586047

A Markov Decision Process Approach to Active Meta Learning

@article{Wang2020AMD,
  title={A Markov Decision Process Approach to Active Meta Learning},
  author={B. Wang and Alec Koppel and V. Krishnamurthy},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.04950}
}
  • B. Wang, Alec Koppel, V. Krishnamurthy
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • In supervised learning, we fit a single statistical model to a given data set, assuming that the data is associated with a singular task, which yields well-tuned models for specific use, but does not adapt well to new contexts. By contrast, in meta-learning, the data is associated with numerous tasks, and we seek a model that may perform well on all tasks simultaneously, in pursuit of greater generalization. One challenge in meta-learning is how to exploit relationships between tasks and… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 56 REFERENCES
    Weighted Meta-Learning
    • 6
    • PDF
    Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
    • 2,887
    • Highly Influential
    • PDF
    Meta-Learning without Memorization
    • 35
    • PDF
    Model-Agnostic Meta-Learning using Runge-Kutta Methods
    • 2
    • PDF
    Meta-Learning with Implicit Gradients
    • 132
    • PDF
    Bilevel Programming for Hyperparameter Optimization and Meta-Learning
    • 162
    • PDF
    On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms
    • 54
    • PDF
    SAMPLE MEAN BASED INDEX POLICIES WITH O(logn) REGRET FOR THE MULTI-ARMED BANDIT PROBLEM
    • 470
    Boosting for transfer learning
    • 1,237
    • Highly Influential
    • PDF
    Markov Decision Processes: Discrete Stochastic Dynamic Programming
    • M. Puterman
    • Mathematics, Computer Science
    • Wiley Series in Probability and Statistics
    • 1994
    • 10,613
    • Highly Influential