Image de couverture de livre

Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Oh, Junsoo, Huang, Wei, Suzuki, Taiji
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

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

Provable Benefit of Cutout and CutMix for Feature Learning
par: Oh, Junsoo, et autres
Publié: (2024)

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
par: Jiang, Jiarui, et autres
Publié: (2025)

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

From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
par: Oh, Junsoo, et autres
Publié: (2025)

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

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

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

On the Role of Label Noise in the Feature Learning Process
par: Han, Andi, et autres
Publié: (2025)

How do Transformers perform In-Context Autoregressive Learning?
par: Sander, Michael E., et autres
Publié: (2024)

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

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)

Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
par: Park, Jongho, et autres
Publié: (2024)

Can Mamba Learn In Context with Outliers? A Theoretical Generalization Analysis
par: Li, Hongkang, et autres
Publié: (2025)

Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
par: Bu, Dake, et autres
Publié: (2024)

On the Comparison between Multi-modal and Single-modal Contrastive Learning
par: Huang, Wei, et autres
Publié: (2024)

How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
par: Higuchi, Rei, et autres
Publié: (2026)

Provable In-Context Vector Arithmetic via Retrieving Task Concepts
par: Bu, Dake, et autres
Publié: (2025)

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
par: Chen, Yihang, et autres
Publié: (2024)

Is Mamba Capable of In-Context Learning?
par: Grazzi, Riccardo, et autres
Publié: (2024)

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

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)

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

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

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

Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations
par: Oko, Kazusato, et autres
Publié: (2024)

Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models
par: Higuchi, Rei, et autres
Publié: (2025)

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

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

Dimensionality-induced information loss of outliers in deep neural networks
par: Uematsu, Kazuki, et autres
Publié: (2024)

Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation
par: Kim, Jinuk, et autres
Publié: (2026)

Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
par: Huang, Wei, et autres
Publié: (2026)

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

Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons
par: Huang, Wei, et autres
Publié: (2023)

From Saddle Points Toward Global Minima: A Newton-Type Method on Wasserstein Space
par: Lascu, Razvan-Andrei, et autres
Publié: (2026)

Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
par: Hübotter, Jonas, et autres
Publié: (2025)

Can Transformers Break Encryption Schemes via In-Context Learning?
par: Korrapati, Jathin, et autres
Publié: (2025)