Attention Kernels for Learning Maps Between Heavy-Tailed Measures

cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Comments: 32 pages, 17 figures, accepted to NeurIPS 2026 Workshop on AI for Stochastic Dynamics

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Learning Probabilistic Filters with Strictly Proper Scoring Rules
• In-Context Operator Learning on the Space of Probability Measures
• FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
• Transformer Quality in Linear Time
• Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
• Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
• Theory, Analysis, and Best Practices for Sigmoid Self-Attention
• Rethinking Attention: Polynomial Alternatives to Softmax in Transformers
• A Study on ReLU and Softmax in Transformer
• Measure-to-measure Regression with Transformers
• Attention Is All You Need
• A Mathematical Theory of Attention
• Replacing softmax with ReLU in Vision Transformers
• Deep Sets

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks