FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees

نویسندگان

  • Konstantinos Pitas
  • Mike Davies
  • Pierre Vandergheynst
چکیده

Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers, often with little or no drop in classification accuracy. However, most of the existing pruning schemes either have to be applied during training or require a costly retraining procedure after pruning to regain classification accuracy. We start by proposing a cheap pruning algorithm for fully connected DNN layers based on difference of convex functions (DC) optimisation, that requires little or no retraining. We then provide a theoretical analysis for the growth in the Generalization Error (GE) of a DNN for the case of bounded perturbations to the hidden layers, of which weight pruning is a special case. Our pruning method is orders of magnitude faster than competing approaches, while our theoretical analysis sheds light to previously observed problems in DNN pruning. Experiments on commnon feedforward neural networks validate our results.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Anelia Angelova In Partial Fulfillment

Could a training example be detrimental to learning? Contrary to the common belief that more training data is needed for better generalization, we show that the learning algorithm might be better off when some training examples are discarded. In other words, the quality of the examples matters. We explore a general approach to identify examples that are troublesome for learning with a given mod...

متن کامل

A Fast, Bottom-Up Decision Tree Pruning Algorithm with Near-Optimal Generalization

In this work, we present a new bottom-up algorithm for decision tree pruning that is very e cient (requiring only a single pass through the given tree), and prove a strong performance guarantee for the generalization error of the resulting pruned tree. We work in the typical setting in which the given tree T may have been derived from the given training sample S, and thus may badly over t S. In...

متن کامل

A Fast , Bottom - Up Decision

In this work, we present a new bottom-up algorithm for decision tree pruning that is very eecient (requiring only a single pass through the given tree), and prove a strong performance guarantee for the generalization error of the resulting pruned tree. We work in the typical setting in which the given tree T may have been derived from the given training sample S, and thus may badly overrt S. In...

متن کامل

Learning Small Trees and Graphs that Generalize

In this Thesis we study issues related to learning small tree and graph formed classifiers. First, we study reduced error pruning of decision trees and branching programs. We analyze the behavior of a reduced error pruning algorithm for decision trees under various probabilistic assumptions on the pruning data. As a result we get, e.g., new upper bounds for the probability of replacing a tree t...

متن کامل

Modeling of measurement error in refractive index determination of fuel cell using neural network and genetic algorithm

Abstract: In this paper, a method for determination of refractive index in membrane of fuel cell on basis of three-longitudinal-mode laser heterodyne interferometer is presented. The optical path difference between the target and reference paths is fixed and phase shift is then calculated in terms of refractive index shift. The measurement accuracy of this system is limited by nonlinearity erro...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2018