Progressive Knowledge Distillation: Constructing Ensembles for Efficient Inference

Don Dennis, Abhishek Shetty, Anish Prasad Sevekari, Kazuhito Koishida, Virginia Smith

Keywords: progressive distillation, anytime inference, efficient inference, resource constrained ML, devices

Abstract: Knowledge distillation is commonly used to compress an ensemble of models into a single model. In this work we study the problem of progressive distillation: Given a large, pretrained teacher model $g$, we seek to decompose the model into an ensemble of smaller, low-inference cost student models $f_i$. The resulting ensemble allows for flexibly tuning accuracy vs. inference cost, which can be useful for a multitude of applications in efficient inference. Our method, B-DISTIL, uses a boosting procedure that allows function composition based aggregation rules to construct expressive ensembles with similar performance as $g$ using much smaller student models. We demonstrate the effectiveness of B-DISTIL by decomposing pretrained models across a variety of image, speech, and sensor datasets. Our method comes with strong theoretical guarantees in terms of convergence as well as generalization.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning