Methods › General › Regularization › Adaptive Dropout

Adaptive Dropout

15 papers tagged archive 2025-07-28

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.

PaperSourceSee Code · mabirck/adaptative-dropout-pytorch

In Syntology repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: listed only). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2506.12738) is about this method is not checked.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:2506.12738 (its page on Syntology).

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 15 · with a code link: 3 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 15 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 15 of 15, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

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.

TaskPapers
Denoising2
Federated Learning2
Attribute1
Bayesian Inference1
Blind Super-Resolution1
Contrastive Learning1
Deep Learning1
Image Classification1
Image Restoration1
Image Super-Resolution1
Meta-Learning1
Network Pruning1
Optical Character Recognition1
Optical Character Recognition (OCR)1
Quantization1
Retrieval-augmented Generation1
STS1
Semantic Textual Similarity1
Sentence1
Sentence Embeddings1

Usage over time archive 2025-07-28

Papers per year tagged with Adaptive Dropout: 2013 to 2025, peak 7 7 0 2013: 1 paper 2013 2014: 0 papers 2014 2015: 0 papers 2015 2016: 1 paper 2016 2017: 0 papers 2017 2018: 0 papers 2018 2019: 0 papers 2019 2020: 2 papers 2020 2021: 1 paper 2021 2022: 0 papers 2022 2023: 2 papers 2023 2024: 1 paper 2024 2025: 7 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (15 dated). Bars are counts, not a trend claim.

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

Regularization

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