Imagen de Portada

A Theoretical Analysis of Mamba's Training Dynamics: Filtering Relevant Features for Generalization in State Space Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shandirasegaran, Mugunthan, Li, Hongkang, Zhang, Songyang, Wang, Meng, Zhang, Shuai
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Can Mamba Learn In Context with Outliers? A Theoretical Generalization Analysis
por: Li, Hongkang, et al.
Publicado: (2025)

Theoretical Analysis of Contrastive Learning under Imbalanced Data: From Training Dynamics to a Pruning Solution
por: Liao, Haixu, et al.
Publicado: (2026)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
por: Li, Hongkang, et al.
Publicado: (2024)

When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
por: Li, Hongkang, et al.
Publicado: (2025)

Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis
por: Li, Hongkang, et al.
Publicado: (2024)

Theoretical Learning Performance of Graph Neural Networks: The Impact of Jumping Connections and Layer-wise Sparsification
por: Sun, Jiawei, et al.
Publicado: (2025)

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
por: Li, Hongkang, et al.
Publicado: (2024)

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
por: Li, Dongyuan, et al.
Publicado: (2024)

How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance
por: Li, Hongkang, et al.
Publicado: (2024)

DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models
por: Yuan, Haonan, et al.
Publicado: (2024)

PerfMamba: Performance Analysis and Pruning of Selective State Space Models
por: Asif, Abdullah Al, et al.
Publicado: (2025)

STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model
por: Li, Lincan, et al.
Publicado: (2024)

Adaptive State-Space Mamba for Real-Time Sensor Data Anomaly Detection
por: Zhang, Alice, et al.
Publicado: (2025)

Efficient Training of Large-Scale AI Models Through Federated Mixture-of-Experts: A System-Level Approach
por: Chen, Xiaobing, et al.
Publicado: (2025)

BarcodeMamba: State Space Models for Biodiversity Analysis
por: Gao, Tiancheng, et al.
Publicado: (2024)

EchoMamba4Rec: Harmonizing Bidirectional State Space Models with Spectral Filtering for Advanced Sequential Recommendation
por: Wang, Yuda, et al.
Publicado: (2024)

FR-Mamba: Time-Series Physical Field Reconstruction Based on State Space Model
por: Long, Jiahuan, et al.
Publicado: (2025)

Swimba: Switch Mamba Model Scales State Space Models
por: Du, Zhixu, et al.
Publicado: (2026)

MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification
por: Zhang, Da, et al.
Publicado: (2026)

Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
por: Han, Xu, et al.
Publicado: (2024)

Characterizing the Behavior of Training Mamba-based State Space Models on GPUs
por: Baruah, Trinayan, et al.
Publicado: (2025)

Mamba-3: Improved Sequence Modeling using State Space Principles
por: Lahoti, Aakash, et al.
Publicado: (2026)

MambaJSCC: Adaptive Deep Joint Source-Channel Coding with Generalized State Space Model
por: Wu, Tong, et al.
Publicado: (2024)

MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Control
por: Kumar, Sahil, et al.
Publicado: (2026)

How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
por: Li, Hongkang, et al.
Publicado: (2024)

Graph Mamba: Towards Learning on Graphs with State Space Models
por: Behrouz, Ali, et al.
Publicado: (2024)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
por: Zhu, Lianghui, et al.
Publicado: (2024)

Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data
por: Zhang, Bingjie, et al.
Publicado: (2025)

MambaByte: Token-free Selective State Space Model
por: Wang, Junxiong, et al.
Publicado: (2024)

Mamba State-Space Models Are Lyapunov-Stable Learners
por: Halloran, John T., et al.
Publicado: (2024)

Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
por: Zhan, Zheng, et al.
Publicado: (2025)

BarcodeMamba+: Advancing State-Space Models for Fungal Biodiversity Research
por: Gao, Tiancheng, et al.
Publicado: (2025)

Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection
por: Wang, Xiancheng, et al.
Publicado: (2025)

Mixture-of-Experts for Distributed Edge Computing with Channel-Aware Gating Function
por: Song, Qiuchen, et al.
Publicado: (2025)

From Generalization Analysis to Optimization Designs for State Space Models
por: Liu, Fusheng, et al.
Publicado: (2024)

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting
por: Eddin, Mohamad Hakam Shams, et al.
Publicado: (2025)

MemMamba: Rethinking Memory Patterns in State Space Model
por: Wang, Youjin, et al.
Publicado: (2025)

Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL
por: Lv, Qi, et al.
Publicado: (2024)

Mamba: Linear-Time Sequence Modeling with Selective State Spaces
por: Gu, Albert, et al.
Publicado: (2023)

MambaLRP: Explaining Selective State Space Sequence Models
por: Jafari, Farnoush Rezaei, et al.
Publicado: (2024)