# Training Deep Neural Networks via Direct Loss Minimization

Source: [Training Deep Neural Networks via Direct Loss Minimization](<https://www.sota2.com/research/paper/68fa62851e209131ce9f9d70>)

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

Data updated: 2025-10-25T20:21:33.904Z

Authors: Yang Song, Alexander G. Schwing, Richard S. Zemel, Raquel Urtasun

Published: 2015-11-19T22:02:26.000Z

## Abstract

Supervised training of deep neural nets typically relies on minimizing cross-entropy. However, in many domains, we are interested in performing well on metrics specific to the application. In this paper we propose a direct loss minimization approach to train deep neural networks, which provably minimizes the application-specific loss function. This is often non-trivial, since these functions are neither smooth nor decomposable and thus are not amenable to optimization with standard gradient-based methods. We demonstrate the effectiveness of our approach in the context of maximizing average precision for ranking problems. Towards this goal, we develop a novel dynamic programming algorithm that can efficiently compute the weight updates. Our approach proves superior to a variety of baselines in the context of action classification and object detection, especially in the presence of label noise.

## 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/1511.06411>)

[PDF](<https://arxiv.org/pdf/1511.06411.pdf>)
