Papers › UNAS: Differentiable Architecture Search Meets Reinforcement Learning

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

16 Dec 2019CVPR 2020 6arXiv:1912.07651archive 2025-07-28

Arash Vahdat, Arun Mallya, Ming-Yu Liu, Jan Kautz

Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demonstrated promising results while maintaining a search cost orders of magnitude lower than reinforcement learning (RL) based NAS. However, DNAS models can only optimize differentiable loss functions in search, and they require an accurate differentiable approximation of non-differentiable criteria. In this work, we present UNAS, a unified framework for NAS, that encapsulates recent DNAS and RL-based approaches under one framework. Our framework brings the best of both worlds, and it enables us to search for architectures with both differentiable and non-differentiable criteria in one unified framework while maintaining a low search cost. Further, we introduce a new objective function for search based on the generalization gap that prevents the selection of architectures prone to overfitting. We present extensive experiments on the CIFAR-10, CIFAR-100, and ImageNet datasets and we perform search in two fundamentally different search spaces. We show that UNAS obtains the state-of-the-art average accuracy on all three datasets when compared to the architectures searched in the DARTS space. Moreover, we show that UNAS can find an efficient and accurate architecture in the ProxylessNAS search space, that outperforms existing MobileNetV2 based architectures. The source code is available at https://github.com/NVlabs/unas .

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

NVlabs/unas officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Neural Architecture Search Reinforcement Learning Reinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 Convolution Adam Average Pooling Batch Normalization Convolution Cutout DARTS DNAS Depthwise Convolution Depthwise Separable Convolution Differentiable NAS DropPath Gumbel Softmax Inverted Residual Block Pointwise Convolution ProxylessNAS REINFORCE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections