# Discretization-Aware Architecture Search

Source: [Discretization-Aware Architecture Search](<https://www.sota2.com/research/paper/68fa67ec1e209131cea1929b>)

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

Data updated: 2025-10-25T22:25:00.051Z

Authors: Yunjie Tian, Chang Liu, Lingxi Xie, Jianbin Jiao, Qixiang Ye

Published: 2020-07-07T01:18:58.000Z

## Abstract

The search cost of neural architecture search (NAS) has been largely reduced by weight-sharing methods. These methods optimize a super-network with all possible edges and operations, and determine the optimal sub-network by discretization, \\textit{i.e.}, pruning off weak candidates. The discretization process, performed on either operations or edges, incurs significant inaccuracy and thus the quality of the final architecture is not guaranteed. This paper presents discretization-aware architecture search (DA\\textsuperscript{2}S), with the core idea being adding a loss term to push the super-network towards the configuration of desired topology, so that the accuracy loss brought by discretization is largely alleviated. Experiments on standard image classification benchmarks demonstrate the superiority of our approach, in particular, under imbalanced target network configurations that were not studied before.

## 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/2007.03154>)

[PDF](<https://arxiv.org/pdf/2007.03154.pdf>)