Methods › General › Output Functions › Sparsemax

Sparsemax

27 papers tagged archive 2025-07-28

Introduced by André F. T. Martins et al. in From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification

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

Sparsemax is a type of activation/output function similar to the traditional softmax, but able to output sparse probabilities.

sparsemax(z) = arg_(p∈Δᴷ⁻¹)min||p - z||²

PaperSourceSee Code · vene/sparse-structured-attention

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: sparsemax and its structured counterparts; Dynamic Attention with Sparsemax for Sparse Autoencoders.

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: 27 · with a code link: 14 · where Syntology ran a sample: 7 (6 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 (7 of 27 tagged: 6 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 27 of 27, 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 51 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
Machine Translation4
Translation4
General Classification3
Language Modeling3
Language Modelling3
Decoder2
Morphological Inflection2
Question Answering2
Text Classification2
Visual Question Answering2
Visual Question Answering (VQA)2
text-classification2
Abstractive Text Summarization1
Audio Classification1
Autonomous Driving1
Conformal Prediction1
Dialogue Generation1
Diversity1
Document Classification1
Hallucination1

Usage over time archive 2025-07-28

Papers per year tagged with Sparsemax: 2016 to 2025, peak 7 7 0 2016: 1 paper 2016 2017: 0 papers 2017 2018: 1 paper 2018 2019: 4 papers 2019 2020: 7 papers 2020 2021: 5 papers 2021 2022: 2 papers 2022 2023: 2 papers 2023 2024: 2 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (27 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