Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
May 3, 2021
Speakers
Wuyang Chen
Speaker · 0 followers
Xinyu Gong
Speaker · 0 followers
Zhangyang Wang
Speaker · 1 follower
About
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy resource consumption and often incurring search bias due to truncated training or approximations. Can we select the best neural architectures without involving any training and eliminate a drastic portion of the search cost? We provide an affirmative answer, by proposing a novel framework called \textit{training-free neural architecture search} ($\textbf{TE-NAS}$). TE-NAS ranks architectures by analyzing the spectrum of the neural tangent kernel (NTK), and the number of linear regions in the input space. Both are motivated by recent theory advances in deep networks, and can be computed without any training. We show that: (1) these two measurements imply the $\textit{trainability}$ and $\textit{expressivity}$ of a neural network; and (2) they strongly correlate with the network's actual test accuracy. Further on, we design a pruning-based NAS mechanism to achieve a more flexible and superior trade-off between the trainability and expressivity during the search. In NAS-Bench-201 and DARTS search spaces, TE-NAS completes high-quality search but only costs $\textbf{0.5}$ and $\textbf{4}$ GPU hours with one 1080Ti on CIFAR-10 and ImageNet, respectively. We hope our work to inspire more attempts in bridging between the theoretic findings of deep networks and practical impacts in real NAS applications.Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy resource consumption and often incurring search bias due to truncated training or approximations. Can we select the best neural architectures without involving any training and eliminate a drastic portion of the search cost? We provide an affirmative answer, by p…
Categories
AI & Data Science
Category · 10.8k presentations
About ICLR 2021
The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study
Watch later
Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
Watch later
Training a First-Order Theorem Prover from Synthetic Data
Watch later
Vlad Firoiu, …
Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity
Watch later
Memory Optimization for Deep Networks
Watch later
Aashaka Shah, …