Implicit Bias in State Space Models and Linear Autoregressive Training
cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Interpretable Time Series Autoregression for Periodicity Quantification
- Partially Hidden Markov Chain Linear Autoregressive model: inference and forecasting
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Efficiently Modeling Long Sequences with Structured State Spaces
- The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
- Gradient Descent Maximizes the Margin of Homogeneous Neural Networks
- Transformers as Support Vector Machines
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