activity
20182021
most citedNAS-Bench-101: Towards Reproducible Neural Architecture Search

252 citations · 293 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG20212 cited

Hyperparameter Transfer Learning with Adaptive Complexity

Samuel Horváth, Aaron Klein, Peter Richtárik +1

Bayesian optimization (BO) is a sample efficient approach to automatically tune the hyperparameters of machine learning models. In practice, one frequently has to solve similar hyp…

cs.LG20212 cited

BORE: Bayesian Optimization by Density-Ratio Estimation

Louis C. Tiao, Aaron Klein, Matthias Seeger +3

Bayesian optimization (BO) is among the most effective and widely-used blackbox optimization methods. BO proposes solutions according to an explore-exploit trade-off criterion enco…

cs.LG2020

Model-based Asynchronous Hyperparameter and Neural Architecture Search

Aaron Klein, Louis C. Tiao, Thibaut Lienart +2

We introduce a model-based asynchronous multi-fidelity method for hyperparameter and neural architecture search that combines the strengths of asynchronous Hyperband and Gaussian p…

cs.LG20193 cited

Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings

Matilde Gargiani, Aaron Klein, Stefan Falkner +1

We propose probabilistic models that can extrapolate learning curves of iterative machine learning algorithms, such as stochastic gradient descent for training deep networks, based…

cs.LG201933 cited

Tabular Benchmarks for Joint Architecture and Hyperparameter Optimization

Aaron Klein, Frank Hutter

Due to the high computational demands executing a rigorous comparison between hyperparameter optimization (HPO) methods is often cumbersome. The goal of this paper is to facilitate…

cs.LG2019

Meta-Surrogate Benchmarking for Hyperparameter Optimization

Aaron Klein, Zhenwen Dai, Frank Hutter +2

Despite the recent progress in hyperparameter optimization (HPO), available benchmarks that resemble real-world scenarios consist of a few and very large problem instances that are…