# Frustratingly Easy Model Generalization by Dummy Risk Minimization

Source: [Frustratingly Easy Model Generalization by Dummy Risk Minimization](<https://www.sota2.com/research/paper/68fa70c91e209131cea4d182>)

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

Data updated: 2025-10-26T01:49:52.893Z

Authors: Juncheng Wang, Jindong Wang, Xixu Hu, Shujun Wang, Xing Xie

Published: 2023-08-04T12:43:54.000Z

## Abstract

Empirical risk minimization (ERM) is a fundamental machine learning paradigm. However, its generalization ability is limited in various tasks. In this paper, we devise Dummy Risk Minimization (DuRM), a frustratingly easy and general technique to improve the generalization of ERM. DuRM is extremely simple to implement: just enlarging the dimension of the output logits and then optimizing using standard gradient descent. Moreover, we validate the efficacy of DuRM on both theoretical and empirical analysis. Theoretically, we show that DuRM derives greater variance of the gradient, which facilitates model generalization by observing better flat local minima. Empirically, we conduct evaluations of DuRM across different datasets, modalities, and network architectures on diverse tasks, including conventional classification, semantic segmentation, out-of-distribution generalization, adverserial training, and long-tailed recognition. Results demonstrate that DuRM could consistently improve the performance under all tasks with an almost free lunch manner. Furthermore, we show that DuRM is compatible with existing generalization techniques and we discuss possible limitations. We hope that DuRM could trigger new interest in the fundamental research on risk minimization.

## 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/2308.02287>)

[PDF](<https://arxiv.org/pdf/2308.02287.pdf>)
