Self-driving laboratories for chemistry and materials science
Self-driving laboratories (SDLs) promise an accelerated application of the scientific method.
Through the automation of experimental workflows, along with autonomous experimental …
Through the automation of experimental workflows, along with autonomous experimental …
Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges
Most machine learning algorithms are configured by a set of hyperparameters whose values
must be carefully chosen and which often considerably impact performance. To avoid a time …
must be carefully chosen and which often considerably impact performance. To avoid a time …
Symbolic discovery of optimization algorithms
We present a method to formulate algorithm discovery as program search, and apply it to
discover optimization algorithms for deep neural network training. We leverage efficient …
discover optimization algorithms for deep neural network training. We leverage efficient …
SMAC3: A versatile Bayesian optimization package for hyperparameter optimization
Algorithm parameters, in particular hyperparameters of machine learning algorithms, can
substantially impact their performance. To support users in determining well-performing …
substantially impact their performance. To support users in determining well-performing …
True few-shot learning with language models
Pretrained language models (LMs) perform well on many tasks even when learning from a
few examples, but prior work uses many held-out examples to tune various aspects of …
few examples, but prior work uses many held-out examples to tune various aspects of …
Unexpected improvements to expected improvement for bayesian optimization
Expected Improvement (EI) is arguably the most popular acquisition function in Bayesian
optimization and has found countless successful applications, but its performance is often …
optimization and has found countless successful applications, but its performance is often …
On hyperparameter optimization of machine learning algorithms: Theory and practice
Abstract Machine learning algorithms have been used widely in various applications and
areas. To fit a machine learning model into different problems, its hyper-parameters must be …
areas. To fit a machine learning model into different problems, its hyper-parameters must be …
A comprehensive survey of neural architecture search: Challenges and solutions
Deep learning has made substantial breakthroughs in many fields due to its powerful
automatic representation capabilities. It has been proven that neural architecture design is …
automatic representation capabilities. It has been proven that neural architecture design is …
Hyper-parameter optimization: A review of algorithms and applications
T Yu, H Zhu - arxiv preprint arxiv:2003.05689, 2020 - arxiv.org
Since deep neural networks were developed, they have made huge contributions to
everyday lives. Machine learning provides more rational advice than humans are capable of …
everyday lives. Machine learning provides more rational advice than humans are capable of …
[HTML][HTML] Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization
Accurate assessment of undrained shear strength (USS) for soft sensitive clays is a great
concern in geotechnical engineering practice. This study applies novel data-driven extreme …
concern in geotechnical engineering practice. This study applies novel data-driven extreme …