← Search

Neeratyoy Mallik

4 accepted papers

2024

In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization

ICML 2024poster

With the increasing computational costs associated with deep learning, automated hyperparameter optimization methods, strongly relying on black-box Bayesian optimization (BO), face limitations. Freeze-thaw BO offers a promising grey-box alternative, strategically allocating scarce resources increme…

Cited by 10SourcePDFScholar
2023

PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning

NeurIPS 2023poster

Hyperparameters of Deep Learning (DL) pipelines are crucial for their downstream performance. While a large number of methods for Hyperparameter Optimization (HPO) have been developed, their incurred costs are often untenable for modern DL. Consequently, manual experimentation is still the most pre…

2021

DEHB: Evolutionary Hyberband for Scalable, Robust and Efficient Hyperparameter Optimization

IJCAI 2021poster

Modern machine learning algorithms crucially rely on several design decisions to achieve strong performance, making the problem of Hyperparameter Optimization (HPO) more important than ever. Here, we combine the advantages of the popular bandit-based HPO method Hyperband (HB) and the evolutionary se…

2021

HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO

NeurIPS 2021poster

To achieve peak predictive performance, hyperparameter optimization (HPO) is a crucial component of machine learning and its applications. Over the last years, the number of efficient algorithms and tools for HPO grew substantially. At the same time, the community is still lacking realistic, diverse…

Cited by 105SourcecodeScholar