Our vehicle routing optimization algorithm uses 20+ hyperparameters that define how it explores the huge combinatorial space of this NP-complete problem. In a few weeks, SigOpt saved us months of a single engineers’ time to yield a comparable performance improvement. Whenever we change our algorithm it makes us these kind of savings all over again.It’s like having another engineer onboard.” – Marin Saric, Optimoroute

SigOpt lets our users efficiently tune their simulations, getting better results faster than traditional methods, allowing them to leverage Rescale for even more complex models while saving both time and money.” – Adam McKenzie, Rescale

Tune your models automatically

Machine learning models depend on hyperparameters that trade off bias/variance and other key outcomes. SigOpt provides Bayesian hyperparameter optimization using an ensemble of the latest research.

Learn More

Easy Integrations

SigOpt can tune any machine learning model, including popular techniques like gradient boosting, deep neural networks, and support vector machines. SigOpt integrates into any workflow, including REST API, Python, and R.

Learn More

Your Tools, Your Data

SigOpt augments your existing model training cluster, suggesting parameter configurations to maximize any online or offline objective, such as AUC ROC, model accuracy, or revenue. You only send SigOpt your metadata, not the underlying training data or model.

Learn More