Timezone: »
Normalization layers and activation functions are fundamental components in deep networks and typically co-locate with each other. Here we propose to design them using an automated approach. Instead of designing them separately, we unify them into a single tensor-to-tensor computation graph, and evolve its structure starting from basic mathematical functions. Examples of such mathematical functions are addition, multiplication and statistical moments. The use of low-level mathematical functions, in contrast to the use of high-level modules in mainstream NAS, leads to a highly sparse and large search space which can be challenging for search methods. To address the challenge, we develop efficient rejection protocols to quickly filter out candidate layers that do not work well. We also use multi-objective evolution to optimize each layer's performance across many architectures to prevent overfitting. Our method leads to the discovery of EvoNorms, a set of new normalization-activation layers with novel, and sometimes surprising structures that go beyond existing design patterns. For example, some EvoNorms do not assume that normalization and activation functions must be applied sequentially, nor need to center the feature maps, nor require explicit activation functions. Our experiments show that EvoNorms work well on image classification models including ResNets, MobileNets and EfficientNets but also transfer well to Mask R-CNN with FPN/SpineNet for instance segmentation and to BigGAN for image synthesis, outperforming BatchNorm and GroupNorm based layers in many cases.
Author Information
Hanxiao Liu (Google Brain)
Andy Brock (DeepMind)
Karen Simonyan (DeepMind)
Quoc V Le (Google)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Spotlight: Evolving Normalization-Activation Layers »
Fri. Dec 11th 03:20 -- 03:30 AM Room Orals & Spotlights: Health/AutoML/(Soft|Hard)ware
More from the Same Authors
-
2023 Poster: Symbolic Discovery of Optimization Algorithms »
Xiangning Chen · Chen Liang · Da Huang · Esteban Real · Kaiyuan Wang · Hieu Pham · Xuanyi Dong · Thang Luong · Cho-Jui Hsieh · Yifeng Lu · Quoc V Le -
2023 Poster: DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining »
Sang Michael Xie · Hieu Pham · Xuanyi Dong · Nan Du · Hanxiao Liu · Yifeng Lu · Percy Liang · Quoc V Le · Tengyu Ma · Adams Wei Yu -
2022 Poster: Mixture-of-Experts with Expert Choice Routing »
Yanqi Zhou · Tao Lei · Hanxiao Liu · Nan Du · Yanping Huang · Vincent Zhao · Andrew Dai · zhifeng Chen · Quoc V Le · James Laudon -
2022 Poster: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models »
Jason Wei · Xuezhi Wang · Dale Schuurmans · Maarten Bosma · brian ichter · Fei Xia · Ed Chi · Quoc V Le · Denny Zhou -
2022 Poster: Flamingo: a Visual Language Model for Few-Shot Learning »
Jean-Baptiste Alayrac · Jeff Donahue · Pauline Luc · Antoine Miech · Iain Barr · Yana Hasson · Karel Lenc · Arthur Mensch · Katherine Millican · Malcolm Reynolds · Roman Ring · Eliza Rutherford · Serkan Cabi · Tengda Han · Zhitao Gong · Sina Samangooei · Marianne Monteiro · Jacob L Menick · Sebastian Borgeaud · Andy Brock · Aida Nematzadeh · Sahand Sharifzadeh · Mikołaj Bińkowski · Ricardo Barreira · Oriol Vinyals · Andrew Zisserman · Karén Simonyan -
2022 Poster: TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets »
Chengrun Yang · Gabriel Bender · Hanxiao Liu · Pieter-Jan Kindermans · Madeleine Udell · Yifeng Lu · Quoc V Le · Da Huang -
2021 Poster: CoAtNet: Marrying Convolution and Attention for All Data Sizes »
Zihang Dai · Hanxiao Liu · Quoc V Le · Mingxing Tan -
2021 Poster: Searching for Efficient Transformers for Language Modeling »
David So · Wojciech Mańke · Hanxiao Liu · Zihang Dai · Noam Shazeer · Quoc V Le -
2021 Poster: Pay Attention to MLPs »
Hanxiao Liu · Zihang Dai · David So · Quoc V Le -
2020 : Panel Discussion & Closing »
Yejin Choi · Alexei Efros · Chelsea Finn · Kristen Grauman · Quoc V Le · Yann LeCun · Ruslan Salakhutdinov · Eric Xing -
2020 Poster: Transferable Graph Optimizers for ML Compilers »
Yanqi Zhou · Sudip Roy · Amirali Abdolrashidi · Daniel Wong · Peter Ma · Qiumin Xu · Hanxiao Liu · Phitchaya Phothilimtha · Shen Wang · Anna Goldie · Azalia Mirhoseini · James Laudon -
2020 Oral: Transferable Graph Optimizers for ML Compilers »
Yanqi Zhou · Sudip Roy · Amirali Abdolrashidi · Daniel Wong · Peter Ma · Qiumin Xu · Hanxiao Liu · Phitchaya Phothilimtha · Shen Wang · Anna Goldie · Azalia Mirhoseini · James Laudon -
2020 Poster: PyGlove: Symbolic Programming for Automated Machine Learning »
Daiyi Peng · Xuanyi Dong · Esteban Real · Mingxing Tan · Yifeng Lu · Gabriel Bender · Hanxiao Liu · Adam Kraft · Chen Liang · Quoc V Le -
2020 Poster: RandAugment: Practical Automated Data Augmentation with a Reduced Search Space »
Ekin Dogus Cubuk · Barret Zoph · Jonathon Shlens · Quoc V Le -
2020 Oral: PyGlove: Symbolic Programming for Automated Machine Learning »
Daiyi Peng · Xuanyi Dong · Esteban Real · Mingxing Tan · Yifeng Lu · Gabriel Bender · Hanxiao Liu · Adam Kraft · Chen Liang · Quoc V Le -
2020 Poster: Rethinking Pre-training and Self-training »
Barret Zoph · Golnaz Ghiasi · Tsung-Yi Lin · Yin Cui · Hanxiao Liu · Ekin Dogus Cubuk · Quoc V Le -
2020 Oral: Rethinking Pre-training and Self-training »
Barret Zoph · Golnaz Ghiasi · Tsung-Yi Lin · Yin Cui · Hanxiao Liu · Ekin Dogus Cubuk · Quoc V Le -
2020 Poster: Training Generative Adversarial Networks by Solving Ordinary Differential Equations »
Chongli Qin · Yan Wu · Jost Tobias Springenberg · Andy Brock · Jeff Donahue · Timothy Lillicrap · Pushmeet Kohli -
2020 Spotlight: Training Generative Adversarial Networks by Solving Ordinary Differential Equations »
Chongli Qin · Yan Wu · Jost Tobias Springenberg · Andy Brock · Jeff Donahue · Timothy Lillicrap · Pushmeet Kohli -
2020 Poster: Unsupervised Data Augmentation for Consistency Training »
Qizhe Xie · Zihang Dai · Eduard Hovy · Thang Luong · Quoc V Le -
2020 Poster: Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing »
Zihang Dai · Guokun Lai · Yiming Yang · Quoc V Le -
2019 Poster: XLNet: Generalized Autoregressive Pretraining for Language Understanding »
Zhilin Yang · Zihang Dai · Yiming Yang · Jaime Carbonell · Russ Salakhutdinov · Quoc V Le -
2019 Oral: XLNet: Generalized Autoregressive Pretraining for Language Understanding »
Zhilin Yang · Zihang Dai · Yiming Yang · Jaime Carbonell · Russ Salakhutdinov · Quoc V Le -
2019 Poster: CondConv: Conditionally Parameterized Convolutions for Efficient Inference »
Brandon Yang · Gabriel Bender · Quoc V Le · Jiquan Ngiam -
2019 Poster: Large Scale Adversarial Representation Learning »
Jeff Donahue · Karen Simonyan -
2019 Poster: Mixtape: Breaking the Softmax Bottleneck Efficiently »
Zhilin Yang · Thang Luong · Russ Salakhutdinov · Quoc V Le -
2019 Poster: Saccader: Improving Accuracy of Hard Attention Models for Vision »
Gamaleldin Elsayed · Simon Kornblith · Quoc V Le -
2019 Poster: GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism »
Yanping Huang · Youlong Cheng · Ankur Bapna · Orhan Firat · Dehao Chen · Mia Chen · HyoukJoong Lee · Jiquan Ngiam · Quoc V Le · Yonghui Wu · zhifeng Chen -
2019 Poster: High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks »
Ruben Villegas · Arkanath Pathak · Harini Kannan · Dumitru Erhan · Quoc V Le · Honglak Lee -
2018 Poster: Learning to Navigate in Cities Without a Map »
Piotr Mirowski · Matt Grimes · Mateusz Malinowski · Karl Moritz Hermann · Keith Anderson · Denis Teplyashin · Karen Simonyan · koray kavukcuoglu · Andrew Zisserman · Raia Hadsell -
2018 Poster: Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing »
Chen Liang · Mohammad Norouzi · Jonathan Berant · Quoc V Le · Ni Lao -
2018 Spotlight: Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing »
Chen Liang · Mohammad Norouzi · Jonathan Berant · Quoc V Le · Ni Lao -
2018 Poster: DropBlock: A regularization method for convolutional networks »
Golnaz Ghiasi · Tsung-Yi Lin · Quoc V Le -
2018 Poster: The challenge of realistic music generation: modelling raw audio at scale »
Sander Dieleman · Aaron van den Oord · Karen Simonyan -
2017 Symposium: Metalearning »
Risto Miikkulainen · Quoc V Le · Kenneth Stanley · Chrisantha Fernando -
2016 Poster: An Online Sequence-to-Sequence Model Using Partial Conditioning »
Navdeep Jaitly · Quoc V Le · Oriol Vinyals · Ilya Sutskever · David Sussillo · Samy Bengio -
2015 Poster: Natural Neural Networks »
Guillaume Desjardins · Karen Simonyan · Razvan Pascanu · koray kavukcuoglu -
2015 Poster: Semi-supervised Sequence Learning »
Andrew Dai · Quoc V Le -
2015 Poster: Spatial Transformer Networks »
Max Jaderberg · Karen Simonyan · Andrew Zisserman · koray kavukcuoglu -
2015 Spotlight: Spatial Transformer Networks »
Max Jaderberg · Karen Simonyan · Andrew Zisserman · koray kavukcuoglu -
2014 Poster: Sequence to Sequence Learning with Neural Networks »
Ilya Sutskever · Oriol Vinyals · Quoc V Le -
2014 Poster: Two-Stream Convolutional Networks for Action Recognition in Videos »
Karen Simonyan · Andrew Zisserman -
2014 Spotlight: Two-Stream Convolutional Networks for Action Recognition in Videos »
Karen Simonyan · Andrew Zisserman -
2014 Oral: Sequence to Sequence Learning with Neural Networks »
Ilya Sutskever · Oriol Vinyals · Quoc V Le -
2013 Workshop: Randomized Methods for Machine Learning »
David Lopez-Paz · Quoc V Le · Alexander Smola -
2013 Poster: Deep Fisher Networks for Large-Scale Image Classification »
Karen Simonyan · Andrea Vedaldi · Andrew Zisserman -
2013 Spotlight: Deep Fisher Networks for Large-Scale Image Classification »
Karen Simonyan · Andrea Vedaldi · Andrew Zisserman