Optimization
Efficient and Robust Automated Machine Learning
Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum, Frank Hutter
Recent work has started to tackle this automated machine learning (AutoML) problem with the help of efficient Bayesian optimization methods.
Universal Boosting Variational Inference
Neural Information Processing Systems http://nips.cc/
Meta-Learning with Implicit Gradients
Aravind Rajeswaran, Chelsea Finn, Sham M. Kakade, Sergey Levine
Neural Information Processing Systems http://nips.cc/
iMAML algorithm perform better than MAML
We thank the reviewers for the thoughtful feedback! Reviewer #1: Thank you for the thoughtful questions! We do not require convexity of L anywhere. Furthermore, regularity conditions are often needed for analysis but not to run the algorithm. Similarly, iMAML shows promising empirical results.
Coresets for Near-Convex Functions
Empirical risk minimization (ERM) may be used to generalize the result from train to test data.
Bayesian Optimization with Exponential Convergence
Kenji Kawaguchi, Leslie Pack Kaelbling, Tomรกs Lozano-Pรฉrez
This paper presents a Bayesian optimization method with exponential convergence without the need of auxiliary optimization and without the ฮด -cover sampling. Most Bayesian optimization methods require auxiliary optimization: an additional non-convex global optimization problem, which can be time-consuming and hard to implement in practice. Also, the existing Bayesian optimization method with exponential convergence [ 1] requires access to the ฮด -cover sampling, which was considered to be impractical [ 1, 2]. Our approach eliminates both requirements and achieves an exponential convergence rate.
