Methods › General › Output Functions › Adaptive Softmax

Adaptive Softmax

72 papers tagged archive 2025-07-28

Introduced by Edouard Grave et al. in Efficient softmax approximation for GPUs

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Adaptive Softmax is a speedup technique for the computation of probability distributions over words. The adaptive softmax is inspired by the class-based hierarchical softmax, where the word classes are built to minimize the computation time. Adaptive softmax achieves efficiency by explicitly taking into account the computation time of matrix-multiplication on parallel systems and combining it with a few important observations, namely keeping a shortlist of frequent words in the root node and reducing the capacity of rare words.

PaperSourceSee Code · rosinality/adaptive-softmax-pytorch

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: F2-Softmax; WB-Softmax; softmax-CPR; CGF-Softmax; Gumbel-Softmax; Vertex-Softmax; Latent Softmax; Balanced Softmax.

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.

Papers archive 2025-07-28

archive papers tagged: 72 · with a code link: 39 · where Syntology ran a sample: 16 (15 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (16 of 72 tagged: 15 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 72 of 72, 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 96 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
Language Modelling42
Language Modeling31
Decoder7
Machine Translation7
Translation6
Speech Recognition5
speech-recognition5
Sentence4
Text Generation4
Automatic Speech Recognition3
Automatic Speech Recognition (ASR)3
Paraphrase Identification3
Reinforcement Learning (RL)3
Word Embeddings3
Abstractive Text Summarization2
Deep Attention2
Deep Reinforcement Learning2
GPU2
Graph Neural Network2
Music Generation2

Usage over time archive 2025-07-28

Papers per year tagged with Adaptive Softmax: 2016 to 2025, peak 17 17 0 2016: 2 papers 2016 2017: 0 papers 2017 2018: 1 paper 2018 2019: 13 papers 2019 2020: 17 papers 2020 2021: 14 papers 2021 2022: 6 papers 2022 2023: 10 papers 2023 2024: 6 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (72 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

Output Functions

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