Cover Image

How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Wei, Han, Andi, Song, Yujin, Chen, Yilan, Wu, Denny, Zou, Difan, Suzuki, Taiji
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
by: Chen, Yilan, et al.
Published: (2025)

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

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

Pretrained transformer efficiently learns low-dimensional target functions in-context
by: Oko, Kazusato, et al.
Published: (2024)

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

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference
by: Han, Yujin, et al.
Published: (2024)

Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
by: Han, Yujin, et al.
Published: (2025)

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

From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
by: Kawata, Ryotaro, et al.
Published: (2025)

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

On the Feature Learning in Diffusion Models
by: Han, Andi, et al.
Published: (2024)

The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
by: Li, Jichu, et al.
Published: (2026)

Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
by: Han, Yujin, et al.
Published: (2025)

On the Comparison between Multi-modal and Single-modal Contrastive Learning
by: Huang, Wei, et al.
Published: (2024)

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

AesRM: Improving Video Aesthetics with Expert-Level Feedback
by: Han, Yujin, et al.
Published: (2026)

Gradient Descent Robustly Learns the Intrinsic Dimension of Data in Training Convolutional Neural Networks
by: Zhang, Chenyang, et al.
Published: (2025)

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

Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
by: Lee, Jason D., et al.
Published: (2024)

Momentum Does Not Reduce Stochastic Noise in Stochastic Gradient Descent
by: Sato, Naoki, et al.
Published: (2024)

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
by: Tang, Xuan, et al.
Published: (2025)

Capturing Conditional Dependence via Auto-regressive Diffusion Models
by: Huang, Xunpeng, et al.
Published: (2025)

Learning Provably Improves the Convergence of Gradient Descent
by: Song, Qingyu, et al.
Published: (2025)

Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
by: Huang, Wei, et al.
Published: (2026)

Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability
by: Han, Yujin, et al.
Published: (2024)

On The Capacity of Low-Rank Dyadic Fading Channels in the Low-SNR Regime
by: Singh, Kamal
Published: (2023)

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

DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Models
by: Bu, Dake, et al.
Published: (2026)

Provable In-Context Vector Arithmetic via Retrieving Task Concepts
by: Bu, Dake, et al.
Published: (2025)

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
by: Bu, Dake, et al.
Published: (2025)

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

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

Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
by: Naganuma, Hiroki, et al.
Published: (2026)

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

Improving Implicit Regularization of SGD with Preconditioning for Least Square Problems
by: Su, Junwei, et al.
Published: (2024)

Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
by: Ziyin, Liu, et al.
Published: (2024)

A Theoretical Analysis of Noise Geometry in Stochastic Gradient Descent
by: Wang, Mingze, et al.
Published: (2023)

Dual Space Preconditioning for Gradient Descent in the Overparameterized Regime
by: Ghane, Reza, et al.
Published: (2026)

How Does Critical Batch Size Scale in Pre-training?
by: Zhang, Hanlin, et al.
Published: (2024)

Why Does Stochastic Gradient Descent Slow Down in Low-Precision Training?
by: Yun, Vincent-Daniel
Published: (2025)