( events)   Timezone: »  
The 2021 schedule is still incomplete Program Highlights »
Workshop
Workshop on Neural Architecture Search
Arber Zela · Aaron Klein · Frank Hutter · Liam Li · Jan Hendrik Metzen · Jovita Lukasik





Neural Architecture Search (NAS) is an exciting new field of study that is taking representation learning to the next level by allowing us to learn the architectures in a data-driven way that then enables efficient learning of representations. While representation learning removed the need of manual feature engineering, it shifted the manual task to the manual selection of architectures; as a natural next step, NAS replaces this manual architecture selection step, allowing us true end-to-end learning of the architecture, the features, and the final classifier using the features expressed as instantiations of the architecture.

Since the first workshop on NAS at ICLR 2020, there have been many new developments in NAS. Firstly, there has been a large increase in standardized tabular benchmarks and more researchers releasing source code, leading to more rigorous empirical NAS research and also allowing research groups without access to industry-scale compute resources to run thorough experimental evaluations. Secondly, there are now several works aiming for standardized and modularized open-source libraries that allow for both clean evaluations of different approaches without confounding factors and for mixing and matching components of different NAS methods. Finally, by now there are also several applications of NAS beyond its original narrow focus on object recognition, to fields like semantic segmentation, speech recognition, and natural language processing.

In this workshop, we want to push NAS to the next level and aim to address questions (see proposal) which are of particular relevance to the NAS community. In terms of prospective participants, our main targets are machine learning researchers interested in understanding and improving current NAS methods, but ML researchers planning to apply existing NAS methods to novel domains are also amongst the target community.

Welcome + Live Introduction of Fabio Carlucci (Live Introduction)
Invited Talk Fabio Carlucci (Invited Talk 1)
Q&A Fabio Carlucci (Q&A Session)
Poster Spotlight "HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search" (Poster Spotlight)
Poster Spotlight "How Powerful are Performance Predictors in Neural Architecture Search?" (Poster Spotlight)
Poster Spotlight "Overfitting in Bayesian Optimization: an empirical study and early-stopping solution" (Poster Spotlight)
Poster Spotlight "Width transfer: on the (in)variance of width optimization" (Poster Spotlight)
Poster Spotlight "One-Shot Neural Architecture Search Via Compressive Sensing" (Poster Spotlight)
Poster Spotlight "Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structure" (Poster Spotlight)
Poster Spotlight "On Adversarial Robustness: A Neural Architecture Search perspective" (Poster Spotlight)
Poster Spotlight "MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders" (Poster Spotlight)
Poster Spotlight "AlphaNet: Improved Training of Supernet with Alpha-Divergence" (Poster Spotlight)
Poster Spotlight "Flexible Multi-task Networks by Learning Parameter Allocation" (Poster Spotlight)
Poster Session 1 (poster session)
Coffee Break (Break)
Live introduction for Xuanyi Dong (Live intro)
Invited Talk Xuanyi Dong (Invited Talk)
Q&A Xuanyi Dong (Q&A Session)
Live Intro Contributor Talks (Live intro)
Contributor Talk 1 (Invited Talk)
Q&A Contributor Talk 1 (Q&A Session)
Contributor Talk 2 (Invited Talk)
Q&A Contributor Talk 2 (Q&A Session)
Break (break)
Live introduction for Margret Keuper (Live intro)
Invited Talk Margret Keuper (Invited Talk)
Q&A Margret Keuper (Q&A Session)
Poster Spotlight "Making Differentiable Architecture Search less local" (Poster Spotlight)
Poster Spotlight "A multi-objective perspective on tuning hardware and hyperparameters" (Poster Spotlight)
Poster Spotlight "Simulation-based Scoring for Model-based Asynchronous Hyperparameter and Neural Architecture Search" (Poster Spotlight)
Poster Spotlight "AutoHAS: Efficient Hyperparameter and Architecture Search" (Poster Spotlight)
Poster Spotlight "Tensorizing Neural Architecture Search in the Supernet" (Poster Spotlight)
Poster Spotlight "Recovering Quantitative Models of Human Information Processing with Differentiable Architecture Search" (Poster Spotlight)
Poster Spotlight "How does Weight Sharing Help in Neural Architecture Search?" (Poster Spotlight)
Poster Spotlight "Rethinking NAS Operations for Diverse Tasks" (Poster Spotlight)
Poster Spotlight "Cost-aware Adversarial Best Arm Identification" (Poster Spotlight)
Poster Session 2 (Poster Session)
Break
Live introduction for Jeff Clune (Live intro)
Invited Talk Jeff Clune (Invited Talk)
Q&A Jeff Clune (Q&A Session)
Panel Discussion (Discussion Panel)
Closing Remarks