Cover Image

Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Juno, Suzuki, Taiji
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Transformers are Minimax Optimal Nonparametric In-Context Learners
by: Kim, Juno, et al.
Published: (2024)

Transformers Provably Solve Parity Efficiently with Chain of Thought
by: Kim, Juno, et al.
Published: (2024)

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
by: Kim, Juno, et al.
Published: (2023)

Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
by: Yamamoto, Naoya, et al.
Published: (2025)

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
by: Kim, Juno, et al.
Published: (2025)

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
by: Kim, Juno, et al.
Published: (2025)

Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective
by: Takakura, Shokichi, et al.
Published: (2024)

Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning
by: Oh, Junsoo, et al.
Published: (2025)

Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
by: Nishikawa, Naoki, et al.
Published: (2025)

In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning
by: Wakayama, Tomoya, et al.
Published: (2025)

State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
by: Nishikawa, Naoki, et al.
Published: (2024)

Mirror Mean-Field Langevin Dynamics
by: Gu, Anming, et al.
Published: (2025)

Nonconvex Regularization for Feature Selection in Reinforcement Learning
by: Suzuki, Kyohei, et al.
Published: (2025)

How do Transformers perform In-Context Autoregressive Learning?
by: Sander, Michael E., et al.
Published: (2024)

The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
by: Awano, Ryoya, et al.
Published: (2026)

Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer
by: Hsu, Alexander, et al.
Published: (2026)

Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
by: Kawata, Ryotaro, et al.
Published: (2026)

Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
by: Takakura, Shokichi, et al.
Published: (2023)

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
by: Bu, Dake, et al.
Published: (2024)

Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble
by: Nitanda, Atsushi, et al.
Published: (2025)

Deep Two-Way Matrix Reordering for Relational Data Analysis
by: Watanabe, Chihiro, et al.
Published: (2021)

AutoLL: Automatic Linear Layout of Graphs based on Deep Neural Network
by: Watanabe, Chihiro, et al.
Published: (2021)

Test time training enhances in-context learning of nonlinear functions
by: Kuwataka, Kento, et al.
Published: (2025)

Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models
by: Higuchi, Rei, et al.
Published: (2025)

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
by: Jiang, Jiarui, et al.
Published: (2025)

How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
by: Higuchi, Rei, et al.
Published: (2026)

Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
by: Jiang, Jiarui, et al.
Published: (2024)

On the Role of Label Noise in the Feature Learning Process
by: Han, Andi, et al.
Published: (2025)

Global Dynamics of Heavy-Tailed SGDs in Nonconvex Loss Landscape: Characterization and Control
by: Wang, Xingyu, et al.
Published: (2025)

Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations
by: Oko, Kazusato, et al.
Published: (2024)

From Saddle Points Toward Global Minima: A Newton-Type Method on Wasserstein Space
by: Lascu, Razvan-Andrei, et al.
Published: (2026)

Provable In-Context Learning of Nonlinear Regression with Transformers
by: Li, Hongbo, et al.
Published: (2025)

Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime
by: Wu, Diyuan, et al.
Published: (2025)

Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
by: Kawata, Ryotaro, et al.
Published: (2025)

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

Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems
by: Sato, Kanji, et al.
Published: (2022)

Training Dynamics of In-Context Learning in Linear Attention
by: Zhang, Yedi, et al.
Published: (2025)

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
by: Li, Bingrui, et al.
Published: (2024)

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
by: Zhang, Tongcheng, et al.
Published: (2026)

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
by: Chen, Yihang, et al.
Published: (2024)