Imagen de Portada

Softmax as a Lagrangian-Legendrian Seam

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Lee-Jenkins, Christopher R.
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Manifold Trajectories in Next-Token Prediction: From Replicator Dynamics to Softmax Equilibrium
por: Lee-Jenkins, Christopher R.
Publicado: (2025)

Adaptive Sparse Softmax: An Effective and Efficient Softmax Variant
por: Lv, Qi, et al.
Publicado: (2025)

On the Invariants of Softmax Attention
por: Lee, Wonsuk
Publicado: (2026)

CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption
por: Park, Hanjun, et al.
Publicado: (2026)

Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss
por: Pu, Yuanhao, et al.
Publicado: (2026)

The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry
por: Zhang, Michael, et al.
Publicado: (2024)

Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization
por: Rezazadeh, Navid, et al.
Publicado: (2026)

Universal Approximation with Softmax Attention
por: Hu, Jerry Yao-Chieh, et al.
Publicado: (2025)

Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax
por: Hoffmann, Marcel, et al.
Publicado: (2025)

Convergence Rates for Softmax Gating Mixture of Experts
por: Nguyen, Huy, et al.
Publicado: (2025)

NDCG-Consistent Softmax Approximation with Accelerated Convergence
por: Pu, Yuanhao, et al.
Publicado: (2025)

To Softmax, or not to Softmax: that is the question when applying Active Learning for Transformer Models
por: Gonsior, Julius, et al.
Publicado: (2022)

On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts
por: Yan, Fanqi, et al.
Publicado: (2025)

Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
por: Zuhri, Zayd M. K., et al.
Publicado: (2025)

Online Continual Learning via Logit Adjusted Softmax
por: Huang, Zhehao, et al.
Publicado: (2023)

On Least Square Estimation in Softmax Gating Mixture of Experts
por: Nguyen, Huy, et al.
Publicado: (2024)

Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
por: Nguyen, Huy, et al.
Publicado: (2024)

Softmax is not Enough (for Adaptive Conformal Classification)
por: Attar, Navid Akhavan, et al.
Publicado: (2026)

Scalable-Softmax Is Superior for Attention
por: Nakanishi, Ken M.
Publicado: (2025)

On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective
por: Mongaras, Gabriel, et al.
Publicado: (2025)

Beyond Softmax: A Natural Parameterization for Categorical Random Variables
por: Manenti, Alessandro, et al.
Publicado: (2025)

Customizing the Inductive Biases of Softmax Attention using Structured Matrices
por: Kuang, Yilun, et al.
Publicado: (2025)

Binary Hypothesis Testing for Softmax Models and Leverage Score Models
por: Gu, Yuzhou, et al.
Publicado: (2024)

A Lyapunov Analysis of Softmax Policy Gradient for Stochastic Bandits
por: Lattimore, Tor
Publicado: (2026)

Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective
por: Boursier, Etienne, et al.
Publicado: (2025)

Softlog-Softmax Layers and Divergences Contribute to a Computationally Dependable Ensemble Learning
por: Atto, Abdourrahmane Mahamane
Publicado: (2025)

Logit Dynamics in Softmax Policy Gradient Methods
por: Li, Yingru
Publicado: (2025)

Softmax Attention with Constant Cost per Token
por: Heinsen, Franz A.
Publicado: (2024)

Why Softmax Attention Outperforms Linear Attention
por: Deng, Yichuan, et al.
Publicado: (2023)

Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation
por: Lin, Max Qiushi, et al.
Publicado: (2025)

Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax
por: Atarashi, Kyohei, et al.
Publicado: (2025)

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization
por: Masarczyk, Wojciech, et al.
Publicado: (2025)

Adaptive Sampled Softmax with Inverted Multi-Index: Methods, Theory and Applications
por: Chen, Jin, et al.
Publicado: (2025)

Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement Learning
por: Xie, Zixuan, et al.
Publicado: (2026)

Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
por: Nguyen, Huy, et al.
Publicado: (2023)

A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts
por: Nguyen, Huy, et al.
Publicado: (2023)

On Expert Estimation in Hierarchical Mixture of Experts: Beyond Softmax Gating Functions
por: Nguyen, Huy, et al.
Publicado: (2024)

Improving Explainability of Softmax Classifiers Using a Prototype-Based Joint Embedding Method
por: Sit, Hilarie, et al.
Publicado: (2024)

Softmax pin to Cauchy-Poisson Study
por: Jones, Gareth
Publicado: (2026)

Softmax is not Enough (for Sharp Size Generalisation)
por: Veličković, Petar, et al.
Publicado: (2024)