Architecture-Aware Minimization (A $^2$ M): How to Find Flat Minima in Neural Architecture Search

13 March 2025

Matteo Gambella

Fabrizio Pittorino

ArXiv (abs)PDF HTML

Papers citing "Architecture-Aware Minimization (A$^2$M): How to Find Flat Minima in Neural Architecture Search"

19 / 19 papers shown

Title
FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution Robustness Matteo Gambella Fabrizio Pittorino Manuel Roveri OOD 105 3 0 29 Feb 2024
Improving Differentiable Architecture Search via Self-Distillation Xunyu Zhu Jian Li Yong Liu Weiping Wang 74 8 0 11 Feb 2023
$β$ -DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search Peng Ye Tong He Baopu Li Tao Chen Lei Bai Wanli Ouyang OOD 81 7 0 16 Jan 2023
Towards Understanding Sharpness-Aware Minimization Maksym Andriushchenko Nicolas Flammarion AAML 98 142 0 13 Jun 2022
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry Fabrizio Pittorino Antonio Ferraro Gabriele Perugini Christoph Feinauer Carlo Baldassi R. Zecchina 254 26 0 07 Feb 2022
Rethinking Architecture Selection in Differentiable NAS Ruochen Wang Minhao Cheng Xiangning Chen Xiaocheng Tang Cho-Jui Hsieh 79 178 0 10 Aug 2021
Sharpness-Aware Minimization for Efficiently Improving Generalization Pierre Foret Ariel Kleiner H. Mobahi Behnam Neyshabur AAML 199 1,359 0 03 Oct 2020
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators Xiangxiang Chu Xiaoxing Wang Bo Zhang Shun Lu Xiaolin K. Wei Junchi Yan 50 168 0 02 Sep 2020
Entropic gradient descent algorithms and wide flat minima Fabrizio Pittorino Carlo Lucibello Christoph Feinauer Gabriele Perugini Carlo Baldassi Elizaveta Demyanenko R. Zecchina ODL MLT 97 33 0 14 Jun 2020
NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search Xuanyi Dong Yi Yang 144 714 0 02 Jan 2020
Fantastic Generalization Measures and Where to Find Them Yiding Jiang Behnam Neyshabur H. Mobahi Dilip Krishnan Samy Bengio AI4CE 145 611 0 04 Dec 2019
Optimizing Millions of Hyperparameters by Implicit Differentiation Jonathan Lorraine Paul Vicol David Duvenaud DD 130 416 0 06 Nov 2019
Understanding and Robustifying Differentiable Architecture Search Arber Zela T. Elsken Tonmoy Saikia Yassine Marrakchi Thomas Brox Frank Hutter OOD AAML 150 373 0 20 Sep 2019
Once-for-All: Train One Network and Specialize it for Efficient Deployment Han Cai Chuang Gan Tianzhe Wang Zhekai Zhang Song Han OOD 119 1,283 0 26 Aug 2019
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search Yuhui Xu Lingxi Xie Xiaopeng Zhang Xin Chen Guo-Jun Qi Qi Tian H. Xiong 104 610 0 12 Jul 2019
Shaping the learning landscape in neural networks around wide flat minima Carlo Baldassi Fabrizio Pittorino R. Zecchina MLT 73 84 0 20 May 2019
DARTS: Differentiable Architecture Search Hanxiao Liu Karen Simonyan Yiming Yang 206 4,375 0 24 Jun 2018
Visualizing the Loss Landscape of Neural Nets Hao Li Zheng Xu Gavin Taylor Christoph Studer Tom Goldstein 264 1,901 0 28 Dec 2017
A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets P. Chrabaszcz I. Loshchilov Frank Hutter SSeg OOD 173 649 0 27 Jul 2017