# DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional Plasticity

arXiv: https://arxiv.org/abs/2603.16367 · HTML: https://mlsanity.com/paper/2603.16367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MoE theory and gating functions, one of 12 directions in Mixture-of-experts.
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Placed in

- Mixture-of-experts / [MoE theory and gating functions](https://mlsanity.com/moe/moe-theory-and-gating-functions/)

## Builds on (most cited first, 18 of 18)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [Movement Pruning: Adaptive Sparsity by Fine-Tuning](https://mlsanity.com/paper/2005.07683/) (2020)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [Concrete Dropout](https://mlsanity.com/paper/1705.07832/) (2017)
- [Sparse Networks from Scratch: Faster Training without Losing Performance](https://mlsanity.com/paper/1907.04840/) (2019)
- [Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization](https://mlsanity.com/paper/1902.05967/) (2019)
- [Estimating or Propagating Gradients Through Stochastic Neurons](https://mlsanity.com/paper/1305.2982/) (2013)

## Abstract (arXiv)

Dropout is a representative regularization technique that stochastically deactivates hidden units during training to mitigate overfitting. In contrast, standard inference executes the full network with dense computation, so its goal and mechanism differ from conditional computation, where the executed operations depend on the input. This paper organizes DynamicGate-MLP into a single framework that simultaneously satisfies both the regularization view and the conditional-computation view. Instead of a random mask, the proposed model learns gates that decide whether to use each unit (or block), suppressing unnecessary computation while implementing sample-dependent execution that concentrates computation on the parts needed for each input. To this end, we define continuous gate probabilities and, at inference time, generate a discrete execution mask from them to select an execution path. Training controls the compute budget via a penalty on expected gate usage and uses a Straight-Through Estimator (STE) to optimize the discrete mask. We evaluate DynamicGate-MLP on MNIST, CIFAR-10, Tiny-ImageNet, Speech Commands, and PBMC3k, and compare it with various MLP baselines and MoE-style variants. Compute efficiency is compared under a consistent criterion using gate activation ratios and a layerweighted relative MAC metric, rather than wall-clock latency that depends on hardware and backend kernels.