Approximation Algorithms for Cascading Prediction Models

Matthew Streeter
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:4752-4760, 2018.

Abstract

We present an approximation algorithm that takes a pool of pre-trained models as input and produces from it a cascaded model with similar accuracy but lower average-case cost. Applied to state-of-the-art ImageNet classification models, this yields up to a 2x reduction in floating point multiplications, and up to a 6x reduction in average-case memory I/O. The auto-generated cascades exhibit intuitive properties, such as using lower-resolution input for easier images and requiring higher prediction confidence when using a computationally cheaper model.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-streeter18a, title = {Approximation Algorithms for Cascading Prediction Models}, author = {Streeter, Matthew}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {4752--4760}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/streeter18a/streeter18a.pdf}, url = {https://proceedings.mlr.press/v80/streeter18a.html}, abstract = {We present an approximation algorithm that takes a pool of pre-trained models as input and produces from it a cascaded model with similar accuracy but lower average-case cost. Applied to state-of-the-art ImageNet classification models, this yields up to a 2x reduction in floating point multiplications, and up to a 6x reduction in average-case memory I/O. The auto-generated cascades exhibit intuitive properties, such as using lower-resolution input for easier images and requiring higher prediction confidence when using a computationally cheaper model.} }
Endnote
%0 Conference Paper %T Approximation Algorithms for Cascading Prediction Models %A Matthew Streeter %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-streeter18a %I PMLR %P 4752--4760 %U https://proceedings.mlr.press/v80/streeter18a.html %V 80 %X We present an approximation algorithm that takes a pool of pre-trained models as input and produces from it a cascaded model with similar accuracy but lower average-case cost. Applied to state-of-the-art ImageNet classification models, this yields up to a 2x reduction in floating point multiplications, and up to a 6x reduction in average-case memory I/O. The auto-generated cascades exhibit intuitive properties, such as using lower-resolution input for easier images and requiring higher prediction confidence when using a computationally cheaper model.
APA
Streeter, M.. (2018). Approximation Algorithms for Cascading Prediction Models. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:4752-4760 Available from https://proceedings.mlr.press/v80/streeter18a.html.

Related Material