Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures
Published Version
http://jmlr.org/proceedings/papers/v28/bergstra13.htmlMetadata
Show full item recordCitation
Bergstra, J., D. Yamins, and D. D. Cox. 2013. Making a Science of Model Search: Hyperparameter Optimizationin Hundreds of Dimensions for Vision Architectures. Presented at the 30th International Conference on Machine Learning (ICML 2013), Atlanta, Gerorgia, June 16 – 21, 2013. In JMLR Workshop and Conference Proceedings 28 (1) : 115–123.Abstract
Many computer vision algorithms depend on configuration settings that are typically hand-tuned in the course of evaluating the algorithm for a particular data set. While such parameter tuning is often presented as being incidental to the algorithm, correctly setting these parameter choices is frequently critical to realizing a method’s full potential. Compounding matters, these parameters often must be re-tuned when the algorithm is applied to a new problem domain, and the tuning process itself often depends on personal experience and intuition in ways that are hard to quantify or describe. Since the performance of a given technique depends on both the fundamental quality of the algorithm and the details of its tuning, it is sometimes difficult to know whether a given technique is genuinely better, or simply better tuned. In this work, we propose a meta-modeling approach to support automated hyperparameter optimization, with the goal of providing practical tools that replace hand-tuning with a reproducible and unbiased optimization process. Our approach is to expose the underlying expression graph of how a performance metric (e.g. classification accuracy on validation examples) is computed from hyperparameters that govern not only how individual processing steps are applied, but even which processing steps are included. A hyperparameter optimization algorithm transforms this graph into a program for optimizing that performance metric. Our approach yields state of the art results on three disparate computer vision problems: a face-matching verification task (LFW), a face identification task (PubFig83) and an object recognition task (CIFAR-10), using a single broad class of feed-forward vision architectures.Terms of Use
This article is made available under the terms and conditions applicable to Open Access Policy Articles, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#OAPCitable link to this page
http://nrs.harvard.edu/urn-3:HUL.InstRepos:12561000
Collections
- FAS Scholarly Articles [17845]
Contact administrator regarding this item (to report mistakes or request changes)