Main Menu (Mobile)- Block
- Our Research
-
Support Teams
- Overview
- Anatomy and Histology
- Cell and Tissue Culture
- Cryo-Electron Microscopy
- Drosophila Resources
- Electron Microscopy
- Flow Cytometry Shared Resource (FCSR)
- Gene Targeting and Transgenics
- Janelia Experimental Technology
- Light Microscopy
- Media Prep
- Molecular Biology
- Project Pipeline Support
- Project Technical Resources
- Quantitative Genomics
- Scientific Computing Software
- Scientific Computing Systems
- Viral Tools
- Vivarium
- Open Science
- You + Janelia
- About Us
Main Menu - Block
- Overview
- Anatomy and Histology
- Cell and Tissue Culture
- Cryo-Electron Microscopy
- Drosophila Resources
- Electron Microscopy
- Flow Cytometry Shared Resource (FCSR)
- Gene Targeting and Transgenics
- Janelia Experimental Technology
- Light Microscopy
- Media Prep
- Molecular Biology
- Project Pipeline Support
- Project Technical Resources
- Quantitative Genomics
- Scientific Computing Software
- Scientific Computing Systems
- Viral Tools
- Vivarium

Abstract
Metric learning seeks a transformation of the feature space that enhances prediction quality for a given task. In this work we provide PAC-style sample complexity rates for supervised metric learning. We give matching lower- and upper-bounds showing that sample complexity scales with the representation dimension when no assumptions are made about the underlying data distribution. In addition, by leveraging the structure of the data distribution, we provide rates fine-tuned to a specific notion of the intrinsic complexity of a given dataset, allowing us to relax the dependence on representation dimension. We show both theoretically and empirically that augmenting the metric learning optimization criterion with a simple norm-based regularization is important and can help adapt to a dataset’s intrinsic complexity yielding better generalization, thus partly explaining the empirical success of similar regularizations reported in previous works.