# Improved Dropout for Shallow and Deep Learning

arXiv: https://arxiv.org/abs/1602.02220 · HTML: https://mlsanity.com/paper/1602.02220/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2016.

## Built on by (most cited first, 11 of 11)

- [On-the-fly Modulation for Balanced Multimodal Learning](https://mlsanity.com/paper/2410.11582/) (2024)
- [Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation](https://mlsanity.com/paper/2105.09980/) (2021)
- [Learning distinct features helps, provably](https://mlsanity.com/paper/2106.06012/) (2021)
- [A Survey on Dropout Methods and Experimental Verification in Recommendation](https://mlsanity.com/paper/2204.02027/) (2022)
- [WLD-Reg: A Data-dependent Within-layer Diversity Regularizer](https://mlsanity.com/paper/2301.01352/) (2023)
- [Dropout Drops Double Descent](https://mlsanity.com/paper/2305.16179/) (2023)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [CODA: Constructivism Learning for Instance-Dependent Dropout Architecture Construction](https://mlsanity.com/paper/2106.08444/) (2021)
- [[Experiments & Analysis] Evaluating the Feasibility of Sampling-Based Techniques for Training Multilayer Perceptrons](https://mlsanity.com/paper/2306.09293/) (2023)
- [FedTLU: Federated Learning with Targeted Layer Updates](https://mlsanity.com/paper/2412.17692/) (2024)
- [ML-based Predictive Models for Power Consumption in Virtualised O-RANs](https://mlsanity.com/paper/2607.24256/) (2026)

## Abstract (arXiv)

Dropout has been witnessed with great success in training deep neural networks by independently zeroing out the outputs of neurons at random. It has also received a surge of interest for shallow learning, e.g., logistic regression. However, the independent sampling for dropout could be suboptimal for the sake of convergence. In this paper, we propose to use multinomial sampling for dropout, i.e., sampling features or neurons according to a multinomial distribution with different probabilities for different features/neurons. To exhibit the optimal dropout probabilities, we analyze the shallow learning with multinomial dropout and establish the risk bound for stochastic optimization. By minimizing a sampling dependent factor in the risk bound, we obtain a distribution-dependent dropout with sampling probabilities dependent on the second order statistics of the data distribution. To tackle the issue of evolving distribution of neurons in deep learning, we propose an efficient adaptive dropout (named evolutional dropout) that computes the sampling probabilities on-the-fly from a mini-batch of examples. Empirical studies on several benchmark datasets demonstrate that the proposed dropouts achieve not only much faster convergence and but also a smaller testing error than the standard dropout. For example, on the CIFAR-100 data, the evolutional dropout achieves relative improvements over 10% on the prediction performance and over 50% on the convergence speed compared to the standard dropout.