paper-with-me

홈 › Papers

Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds

2018-04-15 · ICLR 2019 5 · Cenk Baykal, Lucas Liebenwein, Igor Gilitschenski, Dan Feldman, Daniela Rus

We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an importance sampling scheme that judiciously defines a sampling distribution over the neural network parameters, and as a result, retains parameters of high importance while discarding redundant ones. We leverage a novel, empirical notion of sensitivity and extend traditional coreset constructions to the application of compressing parameters. Our theoretical analysis establishes guarantees on the size and accuracy of the resulting compressed network and gives rise to generalization bounds that may provide new insights into the generalization properties of neural networks. We demonstrate the practical effectiveness of our algorithm on a variety of neural network configurations and real-world data sets.

📄 PDF Abstract BibTeX arXiv:1804.05345

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsNeural Network Compression

Similar Papers 제목 키워드 기반

On Coresets for Logistic Regression

2018-05-22 · NeurIPS 2018 12 · Alexander Munteanu, Chris Schwiegelshohn, Christian Sohler, David P. Woodruff

Coresets are one of the central methods to facilitate the analysis of large data sets. We continue a recent line of research applying the theory of coresets to logistic regression. First, we show a negative result, namel…

regression

Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions

2022-09-18 · Murad Tukan, Loay Mualem, Alaa Maalouf

Pruning is one of the predominant approaches for compressing deep neural networks (DNNs). Lately, coresets (provable data summarizations) were leveraged for pruning DNNs, adding the advantage of theoretical guarantees on…

Understanding collections of related datasets using dependent MMD coresets

2020-06-24 · Sinead A. Williamson, Jette Henderson

Understanding how two datasets differ can help us determine whether one dataset under-represents certain sub-populations, and provides insights into how well models will generalize across datasets. Representative points …

Data Summarization

Faster PAC Learning and Smaller Coresets via Smoothed Analysis

2020-06-09 · Alaa Maalouf, Ibrahim Jubran, Murad Tukan, Dan Feldman

PAC-learning usually aims to compute a small subset ($\varepsilon$-sample/net) from $n$ items, that provably approximates a given loss function for every query (model, classifier, hypothesis) from a given set of queries,…

PAC learning

AutoCoreset: An Automatic Practical Coreset Construction Framework

2023-05-19 · Alaa Maalouf, Murad Tukan, Vladimir Braverman, Daniela Rus

A coreset is a tiny weighted subset of an input set, that closely resembles the loss function, with respect to a certain set of queries. Coresets became prevalent in machine learning as they have shown to be advantageous…