Papers › Pushing the bounds of dropout

Pushing the bounds of dropout

23 May 2018ICLR 2019 5arXiv:1805.09208archive 2025-07-28

Gábor Melis, Charles Blundell, Tomáš Kočiský, Karl Moritz Hermann, Chris Dyer, Phil Blunsom

We show that dropout training is best understood as performing MAP estimation concurrently for a family of conditional models whose objectives are themselves lower bounded by the original dropout objective. This discovery allows us to pick any model from this family after training, which leads to a substantial improvement on regularisation-heavy language modelling. The family includes models that compute a power mean over the sampled dropout masks, and their less stochastic subvariants with tighter and higher lower bounds than the fully stochastic dropout objective. We argue that since the deterministic subvariant's bound is equal to its objective, and the highest amongst these models, the predominant view of it as a good approximation to MC averaging is misleading. Rather, deterministic dropout is the best available approximation to the true objective.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

deepmind/lamb mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Long Expressive Memory for Sequence Modeling (arXiv:2110.04744; that paper's own run record: 5 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling Penn Treebank (Word Level) 2-layer skip-LSTM + dropout tuning Params 24M #24 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) 2-layer skip-LSTM + dropout tuning Test perplexity 55.3 #24 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) 2-layer skip-LSTM + dropout tuning Validation perplexity 57.1 #24 of 43 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Dropout

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