Methods › General › Output Functions › Sparsemax
Sparsemax
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) = _(p∈Δᴷ⁻¹)min||𝐩 - 𝐳||²
Papers archive 2025-07-28
27 shown of 27, 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.
-
ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm 8 Mar 2025 · 1 repository · arXiv:2503.06092
-
Sparse Activations as Conformal Predictors 20 Feb 2025 · 1 repository · arXiv:2502.14773
-
Joint Learning of Energy-based Models and their Partition Function 30 Jan 2025 · 0 repositories · arXiv:2501.18528
-
Learning with Fitzpatrick Losses 23 May 2024 · 0 repositories · arXiv:2405.14574
-
MixLight: Borrowing the Best of both Spherical Harmonics and Gaussian Models 19 Apr 2024 · 0 repositories · arXiv:2404.12768
-
Subject-specific Deep Neural Networks for Count Data with High-cardinality Categorical Features 18 Oct 2023 · 0 repositories · arXiv:2310.11654
-
FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models 23 May 2023 · 2 repositories · arXiv:2305.14481
-
q-Munchausen Reinforcement Learning 16 May 2022 · 0 repositories · arXiv:2205.07467
-
Are Transformers More Robust? Towards Exact Robustness Verification for Transformers 8 Feb 2022 · 0 repositories · arXiv:2202.03932
-
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration 14 Sep 2021 · 1 repository · arXiv:2109.06619Syntology ran 0 of 5 samples · 5 unverified
-
Sparse Communication via Mixed Distributions 5 Aug 2021 · 1 repository · arXiv:2108.02658Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
-
Sparse Continuous Distributions and Fenchel-Young Losses 4 Aug 2021 · 1 repository · arXiv:2108.01988Syntology ran 0 of 1 samples · 1 unverified
-
Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse Communication 1 Apr 2021 · 0 repositories · arXiv:2104.00755
-
Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arrays 29 Mar 2021 · 0 repositories · arXiv:2103.15305
-
A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification 29 Sep 2020 · 0 repositories · arXiv:2009.13935
-
Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity 3 Jul 2020 · 1 repository · arXiv:2007.01919Syntology ran 0 of 9 samples · 9 unverified
-
Exploring Neural Architectures And Techniques For Typologically Diverse Morphological Inflection 1 Jul 2020 · 0 repositories
-
Sparse and Continuous Attention Mechanisms 12 Jun 2020 · 2 repositories · arXiv:2006.07214Syntology ran 12 of 15 samples · 3 unverified · 2 pointer-only (licence)
-
Pruning and Sparsemax Methods for Hierarchical Attention Networks 8 Apr 2020 · 2 repositories · arXiv:2004.04343
-
Sparse Text Generation 6 Apr 2020 · 1 repository · arXiv:2004.02644
-
GSANet: Semantic Segmentation with Global and Selective Attention 14 Feb 2020 · 0 repositories · arXiv:2003.00830
-
Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection 25 Dec 2019 · 2 repositories · arXiv:1912.11637Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
-
Understanding Multi-Head Attention in Abstractive Summarization 10 Nov 2019 · 0 repositories · arXiv:1911.03898
-
Sparse Sequence-to-Sequence Models 14 May 2019 · 1 repository · arXiv:1905.05702
-
SSN: Learning Sparse Switchable Normalization via SparsestMax 9 Mar 2019 · 1 repository · arXiv:1903.03793
-
Maximum Causal Tsallis Entropy Imitation Learning 22 May 2018 · 0 repositories · arXiv:1805.08336
-
From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification 5 Feb 2016 · 11 repositories · arXiv:1602.02068Syntology ran 8 of 8 samples · 0 unverified · 2 pointer-only (licence)
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.
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