# Designing Compact Neural Architectures via Neuron Gating and Mixed Activation

arXiv: https://arxiv.org/abs/2608.14443 · HTML: https://mlsanity.com/paper/2608.14443/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 52 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search](https://mlsanity.com/paper/1907.05737/) (2019)
- [A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions](https://mlsanity.com/paper/2006.02903/) (2020)
- [Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation](https://mlsanity.com/paper/1904.12760/) (2019)
- [Understanding and Robustifying Differentiable Architecture Search](https://mlsanity.com/paper/1909.09656/) (2019)
- [Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search](https://mlsanity.com/paper/1911.12126/) (2019)
- [DARTS+: Improved Differentiable Architecture Search with Early Stopping](https://mlsanity.com/paper/1909.06035/) (2019)
- [HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation](https://mlsanity.com/paper/2012.03826/) (2020)
- [Automated Reinforcement Learning (AutoRL): A Survey and Open Problems](https://mlsanity.com/paper/2201.03916/) (2022)
- [APAC: Augmented PAttern Classification with Neural Networks](https://mlsanity.com/paper/1505.03229/) (2015)
- [RMDL: Random Multimodel Deep Learning for Classification](https://mlsanity.com/paper/1805.01890/) (2018)
- [FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?](https://mlsanity.com/paper/2205.11656/) (2022)
- [Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems](https://mlsanity.com/paper/2110.00604/) (2021)
- [Enhanced Gradient for Differentiable Architecture Search](https://mlsanity.com/paper/2103.12529/) (2021)
- [Relax DARTS: Relaxing the Constraints of Differentiable Architecture Search for Eye Movement Recognition](https://mlsanity.com/paper/2409.11652/) (2024)
- [OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strength](https://mlsanity.com/paper/2409.14433/) (2024)
- [LiFT: Local Search via Linear Programming for Overfitting-Controlled Transformers](https://mlsanity.com/paper/2606.16243/) (2026)
- [Study and Observation of the Variations of Accuracies for Handwritten Digits Recognition with Various Hidden Layers and Epochs using Convolutional Neural Network](https://mlsanity.com/paper/1809.06187/) (2018)
- [Bilevel Optimization for Neural Architecture Search](https://mlsanity.com/paper/2606.29582/) (2026)
- [Performance Evaluation of Advanced Deep Learning Architectures for Offline Handwritten Character Recognition](https://mlsanity.com/paper/2003.06794/) (2020)
- [Handwritten Digit Recognition: An Ensemble-Based Approach for Superior Performance](https://mlsanity.com/paper/2503.06104/) (2025)

## Abstract (arXiv)

Neural Architecture Search (NAS) is naturally formulated as a bilevel optimization problem, where the upper-level optimizes the architecture using validation performance and the lower-level trains network parameters using training loss. However, NAS is computationally expensive due to discrete architectural decisions, exponentially growing search spaces, and the high cost of training candidate architectures. This work develops a general bilevel optimization framework for NAS across diverse architectures, including MLPs, CNNs, RNNs, and Transformers, to identify compact architectures with strong predictive performance. We propose three scalable formulations that replace discrete neuron- and activation-level decisions with continuous relaxations, enabling differentiable optimization over otherwise combinatorial architecture spaces. These formulations give rise to three NAS methods: NAS based on Neuron Gating (NAS-NG), NAS based on Mixed Activation (NAS-MA), and NAS based on Neuron Gating and Mixed Activation (NAS-NGMA). Experiments on MLPs and CNNs using MNIST and CIFAR-10 show that the proposed methods consistently identify compact architectures with competitive or improved predictive performance. On MNIST, NAS-NGMA achieves 98.68% test accuracy with 7.69M MLP parameters, while NAS-NG achieves 99.63% accuracy with only 0.26M CNN parameters. On CIFAR-10, the proposed methods consistently outperform vanilla DARTS. Further experiments demonstrate that NAS-NG can optimize substantially over-parameterized and literature-optimal architectures, improving accuracy while reducing parameters. These results establish relaxed bilevel optimization as a scalable alternative to discrete NAS and provide a general framework for efficient neuron- and activation-level architecture optimization.