Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Falkner, Stefan"'
Autor:
Tighineanu, Petru, Grossberger, Lukas, Baireuther, Paul, Skubch, Kathrin, Falkner, Stefan, Vinogradska, Julia, Berkenkamp, Felix
Meta-learning is a powerful approach that exploits historical data to quickly solve new tasks from the same distribution. In the low-data regime, methods based on the closed-form posterior of Gaussian processes (GP) together with Bayesian optimizatio
Externí odkaz:
http://arxiv.org/abs/2312.00742
Bayesian optimization (BO) is a popular method to optimize costly black-box functions. While traditional BO optimizes each new target task from scratch, meta-learning has emerged as a way to leverage knowledge from related tasks to optimize new tasks
Externí odkaz:
http://arxiv.org/abs/2307.03565
Publikováno v:
Journal of Machine Learning Research 23(261), 2022
Automated Machine Learning (AutoML) supports practitioners and researchers with the tedious task of designing machine learning pipelines and has recently achieved substantial success. In this paper, we introduce new AutoML approaches motivated by our
Externí odkaz:
http://arxiv.org/abs/2007.04074
We propose probabilistic models that can extrapolate learning curves of iterative machine learning algorithms, such as stochastic gradient descent for training deep networks, based on training data with variable-length learning curves. We study insta
Externí odkaz:
http://arxiv.org/abs/1910.04522
Autor:
Volpp, Michael, Fröhlich, Lukas P., Fischer, Kirsten, Doerr, Andreas, Falkner, Stefan, Hutter, Frank, Daniel, Christian
Transferring knowledge across tasks to improve data-efficiency is one of the open key challenges in the field of global black-box optimization. Readily available algorithms are typically designed to be universal optimizers and, therefore, often subop
Externí odkaz:
http://arxiv.org/abs/1904.02642
Designing RNA molecules has garnered recent interest in medicine, synthetic biology, biotechnology and bioinformatics since many functional RNA molecules were shown to be involved in regulatory processes for transcription, epigenetics and translation
Externí odkaz:
http://arxiv.org/abs/1812.11951
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
ICML 2018 AutoML Workshop
While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal
Externí odkaz:
http://arxiv.org/abs/1807.06906
Modern deep learning methods are very sensitive to many hyperparameters, and, due to the long training times of state-of-the-art models, vanilla Bayesian hyperparameter optimization is typically computationally infeasible. On the other hand, bandit-b
Externí odkaz:
http://arxiv.org/abs/1807.01774
We consider parallel asynchronous Markov Chain Monte Carlo (MCMC) sampling for problems where we can leverage (stochastic) gradients to define continuous dynamics which explore the target distribution. We outline a solution strategy for this setting
Externí odkaz:
http://arxiv.org/abs/1612.00767