Riordan Arrays as Structured Operators for Artificial Intelligence
cs.LG, math.CO
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- Sigmoid functions and exponential Riordan arrays
- Monarch: Expressive Structured Matrices for Efficient and Accurate Training
- NICE: Non-linear Independent Components Estimation
- The Reversible Residual Network: Backpropagation Without Storing Activations
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- HiPPO: Recurrent Memory with Optimal Polynomial Projections
- Power Series Composition in Near-Linear Time
- Neural Operator: Learning Maps Between Function Spaces
- LU decomposition and Toeplitz decomposition of a neural network
- Compute Better Spent: Replacing Dense Layers with Structured Matrices
- Simplified State Space Layers for Sequence Modeling
- Attention Is All You Need
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis