Image de couverture de livre

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jiang, Jiarui, Huang, Wei, Zhang, Miao, Suzuki, Taiji, Nie, Liqiang
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
par: Jiang, Jiarui, et autres
Publié: (2024)

Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning
par: Oh, Junsoo, et autres
Publié: (2025)

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
par: Li, Bingrui, et autres
Publié: (2024)

How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
par: Huang, Wei, et autres
Publié: (2025)

A Polynomial-time Algorithm for Online Sparse Linear Regression with Improved Regret Bound under Weaker Conditions
par: Li, Junfan, et autres
Publié: (2025)

Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
par: Chen, Yilan, et autres
Publié: (2025)

AutoLL: Automatic Linear Layout of Graphs based on Deep Neural Network
par: Watanabe, Chihiro, et autres
Publié: (2021)

In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning
par: Wakayama, Tomoya, et autres
Publié: (2025)

Scaling Law for Stochastic Gradient Descent in Quadratically Parameterized Linear Regression
par: Ding, Shihong, et autres
Publié: (2025)

Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape
par: Kim, Juno, et autres
Publié: (2024)

Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent
par: Zhang, Chenyang, et autres
Publié: (2026)

Transformers are Minimax Optimal Nonparametric In-Context Learners
par: Kim, Juno, et autres
Publié: (2024)

Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
par: Nishikawa, Naoki, et autres
Publié: (2025)

Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
par: Yamamoto, Naoya, et autres
Publié: (2025)

Learning Curves of Stochastic Gradient Descent in Kernel Regression
par: Zhang, Haihan, et autres
Publié: (2025)

Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context
par: Cheng, Xiang, et autres
Publié: (2023)

Stochastic Gradient Descent for Nonparametric Additive Regression
par: Chen, Xin, et autres
Publié: (2024)

Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
par: Qiu, Haomiao, et autres
Publié: (2025)

Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization
par: Chen, Zonghao, et autres
Publié: (2025)

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
par: Kim, Juno, et autres
Publié: (2025)

Test time training enhances in-context learning of nonlinear functions
par: Kuwataka, Kento, et autres
Publié: (2025)

Deep Two-Way Matrix Reordering for Relational Data Analysis
par: Watanabe, Chihiro, et autres
Publié: (2021)

The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
par: Awano, Ryoya, et autres
Publié: (2026)

State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
par: Nishikawa, Naoki, et autres
Publié: (2024)

Transformers Provably Solve Parity Efficiently with Chain of Thought
par: Kim, Juno, et autres
Publié: (2024)

Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective
par: Takakura, Shokichi, et autres
Publié: (2024)

Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
par: Kawata, Ryotaro, et autres
Publié: (2026)

Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
par: Takakura, Shokichi, et autres
Publié: (2023)

Comparing the Moore-Penrose Pseudoinverse and Gradient Descent for Solving Linear Regression Problems: A Performance Analysis
par: Adams, Alex
Publié: (2025)

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
par: Bu, Dake, et autres
Publié: (2024)

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
par: Bu, Dake, et autres
Publié: (2025)

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
par: Zhang, Tongcheng, et autres
Publié: (2026)

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
par: Brown, Gavin, et autres
Publié: (2024)

Harmonized Gradient Descent for Class Imbalanced Data Stream Online Learning
par: Zhou, Han, et autres
Publié: (2025)

Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
par: Wu, Jingfeng, et autres
Publié: (2025)

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
par: Wu, Jingfeng, et autres
Publié: (2025)

Stochastic Normalized Gradient Descent with Momentum for Large-Batch Training
par: Zhao, Shen-Yi, et autres
Publié: (2020)

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
par: Qiu, Haomiao, et autres
Publié: (2025)

Understanding Gradient Descent through the Training Jacobian
par: Belrose, Nora, et autres
Publié: (2024)

Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
par: Kawata, Ryotaro, et autres
Publié: (2025)