Methods › General › Regularization › Adaptive Dropout
Adaptive Dropout
Introduced by Jimmy Ba et al. in Adaptive dropout for training deep neural networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Adaptive Dropout is a regularization technique that extends dropout by allowing the dropout probability to be different for different units. The intuition is that there may be hidden units that can individually make confident predictions for the presence or absence of an important feature or combination of features. Dropout will ignore this confidence and drop the unit out 50% of the time.
Denote the activity of unit j in a deep neural network by aⱼ and assume that its inputs are {aᵢ: i < j}. In dropout, aⱼ is randomly set to zero with probability 0.5. Let mⱼ be a binary variable that is used to mask, the activity aⱼ, so that its value is:
aⱼ = mⱼg ( ∑_(i: i<j)w_(j, i)aᵢ )
where w_(j,i) is the weight from unit i to unit j and g(·) is the activation function and a₀ = 1 accounts for biases. Whereas in standard dropout, mⱼ is Bernoulli with probability $0.5$, adaptive dropout uses adaptive dropout probabilities that depends on input activities:
P(mⱼ = 1|{aᵢ: i < j}) = f ( ∑_(i: i<j)π_(j, i)aᵢ )
where π_(j, i) is the weight from unit i to unit j in the standout network or the adaptive dropout network; f(·) is a sigmoidal function. Here 'standout' refers to a binary belief network is that is overlaid on a neural network as part of the overall regularization technique.
Papers archive 2025-07-28
15 shown of 15, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout 14 Jul 2025 · 0 repositories · arXiv:2507.10430
-
A statistical physics framework for optimal learning 10 Jul 2025 · 0 repositories · arXiv:2507.07907
-
DOTA: Deformable Optimized Transformer Architecture for End-to-End Text Recognition with Retrieval-Augmented Generation 7 May 2025 · 0 repositories · arXiv:2505.04175
-
Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection 12 Mar 2025 · 0 repositories · arXiv:2503.08974
-
Dynamic DropConnect: Enhancing Neural Network Robustness through Adaptive Edge Dropping Strategies 27 Feb 2025 · 1 repository · arXiv:2502.19948
-
2-Tier SimCSE: Elevating BERT for Robust Sentence Embeddings 23 Jan 2025 · 0 repositories · arXiv:2501.13758
-
Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution 1 Jan 2025 · 0 repositories
-
Adaptive Dropout for Pruning Conformers 6 Dec 2024 · 0 repositories · arXiv:2412.04836
-
Communication-Efficient Split Learning via Adaptive Feature-Wise Compression 20 Jul 2023 · 0 repositories · arXiv:2307.10805
-
FedBIAD: Communication-Efficient and Accuracy-Guaranteed Federated Learning with Bayesian Inference-Based Adaptive Dropout 14 Jul 2023 · 0 repositories · arXiv:2307.07172
-
The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization 14 Jun 2021 · 1 repository · arXiv:2106.07769Syntology ran 1 of 1 samples · 0 unverified
-
Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization 11 Oct 2020 · 1 repository · arXiv:2010.05244
-
Adaptive Low-Rank Factorization to regularize shallow and deep neural networks 5 May 2020 · 0 repositories · arXiv:2005.01995
-
Improved Dropout for Shallow and Deep Learning 6 Feb 2016 · 0 repositories · arXiv:1602.02220
-
Adaptive dropout for training deep neural networks 1 Dec 2013 · 0 repositories
Tasks archive 2025-07-28
20 shown of 30 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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