Parallel Broyden Methods for Efficiently Evaluating Nonlinear State Space Models
cs.LG, cs.NA, math.NA
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/ianctanoh/BroyDEER
Terminology
Sources
- Efficiently Modeling Long Sequences with Structured State Spaces
- Simplified State Space Layers for Sequence Modeling
- Parallelizing Linear Recurrent Neural Nets Over Sequence Length
- Denoising Diffusion Implicit Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- Parallelizing non-linear sequential models over the sequence length
- A Unifying Framework for Parallelizing Sequential Models with Linear Dynamical Systems
- A parallel-in-time Newton's method-based ODE solver
- Predictability Enables Parallelization of Nonlinear State Space Models
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