:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autore principale:	Atto, Abdourrahmane Mahamane
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	https://arxiv.org/abs/2506.04297
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Time Distributed Deep Learning Models for Purely Exogenous Forecasting: Application to Water Table Depth Prediction using Weather Image Time Series
di: Salis, Matteo, et al.
Pubblicazione: (2024)

Pure and Physics-Guided Deep Learning Solutions for Spatio-Temporal Groundwater Level Prediction at Arbitrary Locations
di: Salis, Matteo, et al.
Pubblicazione: (2026)

Smooth SCAD: A Raised Cosine SCAD Type Thresholding Rule for Wavelet Denoising
di: Kulkarni, Radhika, et al.
Pubblicazione: (2026)

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

Reusing Softmax Hardware Unit for GELU Computation in Transformers
di: Peltekis, Christodoulos, et al.
Pubblicazione: (2024)

Hardware-Efficient Softmax and Layer Normalization with Guaranteed Normalization for Edge Devices
di: Choi, Dawon, et al.
Pubblicazione: (2026)

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

Implicit Regularization of Gradient Flow on One-Layer Softmax Attention
di: Sheen, Heejune, et al.
Pubblicazione: (2024)

Softmax as a Lagrangian-Legendrian Seam
di: Lee-Jenkins, Christopher R.
Pubblicazione: (2025)

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

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

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

SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference
di: Wang, Wenxun, et al.
Pubblicazione: (2025)

A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification
di: Kühn, Marcel, et al.
Pubblicazione: (2026)

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

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

Scalable Hyperparameter-Divergent Ensemble Training with Automatic Learning Rate Exploration for Large Models
di: Cheng, Hailing, et al.
Pubblicazione: (2026)

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

Minimalist Softmax Attention Provably Learns Constrained Boolean Functions
di: Hu, Jerry Yao-Chieh, et al.
Pubblicazione: (2025)

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

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

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

Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity
di: Shi, Zhongjie, et al.
Pubblicazione: (2026)

Divergent Ensemble Networks: Enhancing Uncertainty Estimation with Shared Representations and Independent Branching
di: Kharbanda, Arnav, et al.
Pubblicazione: (2024)

Towards Understanding Layer Contributions in Tabular In-Context Learning Models
di: Balef, Amir Rezaei, et al.
Pubblicazione: (2025)

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

VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers
di: Wang, Run, et al.
Pubblicazione: (2025)

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

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

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

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

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

In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
di: Collins, Liam, et al.
Pubblicazione: (2024)

On the Invariants of Softmax Attention
di: Lee, Wonsuk
Pubblicazione: (2026)

Batch Ensemble for Variance Dependent Regret in Stochastic Bandits
di: Cassel, Asaf, et al.
Pubblicazione: (2024)

Logit Dynamics in Softmax Policy Gradient Methods
di: Li, Yingru
Pubblicazione: (2025)

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

Why Softmax Attention Outperforms Linear Attention
di: Deng, Yichuan, et al.
Pubblicazione: (2023)

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

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