# UNAS: Differentiable Architecture Search Meets Reinforcement Learning

arXiv: https://arxiv.org/abs/1912.07651 · HTML: https://mlsanity.com/paper/1912.07651/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2019.

## Built on by (most cited first, 21 of 21)

- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Structural Pruning via Latency-Saliency Knapsack](https://mlsanity.com/paper/2210.06659/) (2022)
- [When to Prune? A Policy towards Early Structural Pruning](https://mlsanity.com/paper/2110.12007/) (2021)
- [LANA: Latency Aware Network Acceleration](https://mlsanity.com/paper/2107.10624/) (2021)
- [RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search](https://mlsanity.com/paper/2109.05691/) (2021)
- [HALP: Hardware-Aware Latency Pruning](https://mlsanity.com/paper/2110.10811/) (2021)
- [Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training](https://mlsanity.com/paper/2106.03640/) (2021)
- [Restructurable Activation Networks](https://mlsanity.com/paper/2208.08562/) (2022)
- [Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search](https://mlsanity.com/paper/2304.05405/) (2023)
- [CONetV2: Efficient Auto-Channel Size Optimization for CNNs](https://mlsanity.com/paper/2110.06830/) (2021)
- [Pareto-aware Neural Architecture Generation for Diverse Computational Budgets](https://mlsanity.com/paper/2210.07634/) (2022)
- [BFTrainer: Low-Cost Training of Neural Networks on Unfillable Supercomputer Nodes](https://mlsanity.com/paper/2106.12091/) (2021)
- [CONet: Channel Optimization for Convolutional Neural Networks](https://mlsanity.com/paper/2108.06822/) (2021)
- [You Only Search Once: On Lightweight Differentiable Architecture Search for Resource-Constrained Embedded Platforms](https://mlsanity.com/paper/2208.14446/) (2022)
- [Efficient Model Performance Estimation via Feature Histories](https://mlsanity.com/paper/2103.04450/) (2021)
- [Neural Architecture Retrieval](https://mlsanity.com/paper/2307.07919/) (2023)
- [Meta knowledge assisted Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2504.21545/) (2025)
- [Delve into the Performance Degradation of Differentiable Architecture Search](https://mlsanity.com/paper/2109.13466/) (2021)
- [AutoCoMet: Smart Neural Architecture Search via Co-Regulated Shaping Reinforcement](https://mlsanity.com/paper/2203.15408/) (2022)
- [Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search](https://mlsanity.com/paper/2209.11785/) (2022)
- [An Integrated Approach to Neural Architecture Search for Deep Q-Networks](https://mlsanity.com/paper/2510.19872/) (2025)

## Abstract (arXiv)

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 .