# Some like it tough: Improving model generalization via progressively increasing the training difficulty

Source: [Some like it tough: Improving model generalization via progressively increasing the training difficulty](<https://www.sota2.com/research/paper/68fa6b1b1e209131cea2c3ff>)

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

Data updated: 2025-10-25T23:40:16.064Z

Authors: Hannes Fassold

Published: 2021-10-25T15:54:21.000Z

## Abstract

In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming. This strategy makes sure that the optimizer puts its focus in the later training stages on the more difficult samples, which we identify as the ones with the highest loss in the current mini-batch. The strategy is very easy to integrate into an existing training pipeline and does not necessitate a change of the network model. Experiments on several image classification problems show that mini-batch trimming is able to increase the generalization ability (measured via final test error) of the trained model.

## 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/2110.13058>)

[PDF](<https://arxiv.org/pdf/2110.13058.pdf>)