# Biased Importance Sampling for Deep Neural Network Training

Source: [Biased Importance Sampling for Deep Neural Network Training](<https://www.sota2.com/research/paper/68fa63a41e209131cea00015>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:46:17.527Z

Authors: Angelos Katharopoulos, Fran\\c{c}ois Fleuret

Published: 2017-05-31T18:25:09.000Z

## Abstract

Importance sampling has been successfully used to accelerate stochastic optimization in many convex problems. However, the lack of an efficient way to calculate the importance still hinders its application to Deep Learning.   In this paper, we show that the loss value can be used as an alternative importance metric, and propose a way to efficiently approximate it for a deep model, using a small model trained for that purpose in parallel.   This method allows in particular to utilize a biased gradient estimate that implicitly optimizes a soft max-loss, and leads to better generalization performance. While such method suffers from a prohibitively high variance of the gradient estimate when using a standard stochastic optimizer, we show that when it is combined with our sampling mechanism, it results in a reliable procedure.   We showcase the generality of our method by testing it on both image classification and language modeling tasks using deep convolutional and recurrent neural networks. In particular, our method results in 30% faster training of a CNN for CIFAR10 than when using uniform sampling.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1706.00043>)

[PDF](<https://arxiv.org/pdf/1706.00043.pdf>)
