TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/Sparsemax

Sparsemax

GeneralIntroduced 200027 papers
Source Paper

Description

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

sparsemax(z)=arg⁡_p∈ΔK−1min⁡∣∣p−z∣∣2\text{sparsemax}\left(z\right) = \arg\_{p∈\Delta^{K−1}}\min||\mathbf{p} - \mathbf{z}||^{2}sparsemax(z)=arg_p∈ΔK−1min∣∣p−z∣∣2

Papers Using This Method

ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm2025-03-08Sparse Activations as Conformal Predictors2025-02-20Joint Learning of Energy-based Models and their Partition Function2025-01-30Learning with Fitzpatrick Losses2024-05-23MixLight: Borrowing the Best of both Spherical Harmonics and Gaussian Models2024-04-19Subject-specific Deep Neural Networks for Count Data with High-cardinality Categorical Features2023-10-18FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models2023-05-23$q$-Munchausen Reinforcement Learning2022-05-16Are Transformers More Robust? Towards Exact Robustness Verification for Transformers2022-02-08Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration2021-09-14Sparse Communication via Mixed Distributions2021-08-05Sparse Continuous Distributions and Fenchel-Young Losses2021-08-04Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse Communication2021-04-01Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arrays2021-03-29A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification2020-09-29Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity2020-07-03Exploring Neural Architectures And Techniques For Typologically Diverse Morphological Inflection2020-07-01Sparse and Continuous Attention Mechanisms2020-06-12Pruning and Sparsemax Methods for Hierarchical Attention Networks2020-04-08Sparse Text Generation2020-04-06