Image de couverture de livre

Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Braun, Guillaume, Bao, Han, Huang, Wei, Imaizumi, Masaaki
Format:	Preprint
Publié:	2026
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

Learning a Single Index Model from Anisotropic Data with vanilla Stochastic Gradient Descent
par: Braun, Guillaume, et autres
Publié: (2025)

Neuron Block Dynamics for XOR Classification with Zero-Margin
par: Braun, Guillaume, et autres
Publié: (2026)

Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data
par: Braun, Guillaume, et autres
Publié: (2025)

Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent
par: Imai, Shota, et autres
Publié: (2026)

High-Dimensional Limit of Stochastic Gradient Flow via Dynamical Mean-Field Theory
par: Nishiyama, Sota, et autres
Publié: (2026)

Robust Gradient Descent for Phase Retrieval
par: Buna, Alex, et autres
Publié: (2024)

Effect of Weight Quantization on Learning Models by Typical Case Analysis
par: Kashiwamura, Shuhei, et autres
Publié: (2024)

Iteration and Stochastic First-order Oracle Complexities of Stochastic Gradient Descent using Constant and Decaying Learning Rates
par: Imaizumi, Kento, et autres
Publié: (2024)

Precise gradient descent training dynamics for finite-width multi-layer neural networks
par: Han, Qiyang, et autres
Publié: (2025)

Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers
par: Sakai, Mana, et autres
Publié: (2026)

High-dimensional Contextual Bandit Problem without Sparsity
par: Komiyama, Junpei, et autres
Publié: (2023)

Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality
par: Tamano, Shu, et autres
Publié: (2026)

Approximation of Permutation Invariant Polynomials by Transformers: Efficient Construction in Column-Size
par: Takeshita, Naoki, et autres
Publié: (2025)

Benign Overfitting in Time Series Linear Models with Over-Parameterization
par: Nakakita, Shogo, et autres
Publié: (2022)

Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
par: Nishiyama, Sota, et autres
Publié: (2025)

Finite-Sample Inference for Sparsely Permuted Linear Regression
par: Ota, Hirofumi, et autres
Publié: (2026)

Bayesian Analysis for Over-parameterized Linear Model via Effective Spectra
par: Wakayama, Tomoya, et autres
Publié: (2023)

Minimax Rates of Estimation for Optimal Transport Map between Infinite-Dimensional Spaces
par: Ponnoprat, Donlapark, et autres
Publié: (2025)

Automatic Domain Adaptation by Transformers in In-Context Learning
par: Hataya, Ryuichiro, et autres
Publié: (2024)

Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry
par: Yoshida, Naoki, et autres
Publié: (2025)

Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
par: Sakai, Mana, et autres
Publié: (2025)

Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution
par: Yoshida, Naoki, et autres
Publié: (2024)

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
par: Chen, Baiyuan, et autres
Publié: (2025)

High-dimensional Nonparametric Contextual Bandit Problem
par: Iwazaki, Shogo, et autres
Publié: (2025)

Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses
par: Bao, Han, et autres
Publié: (2025)

Parameter-free Clipped Gradient Descent Meets Polyak
par: Takezawa, Yuki, et autres
Publié: (2024)

Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables
par: Imaizumi, Masaaki, et autres
Publié: (2026)

Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport
par: Ponnoprat, Donlapark, et autres
Publié: (2026)

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

Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks
par: Corlouer, Guillaume, et autres
Publié: (2026)

Gradient Descent as a Shrinkage Operator for Spectral Bias
par: Lucey, Simon
Publié: (2025)

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

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

Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates
par: Goyal, Saumya, et autres
Publié: (2026)

Occam Gradient Descent
par: Kausik, B. N.
Publié: (2024)

Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent
par: Larue, Guillaume, et autres
Publié: (2026)

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

Federated Unlearning with Gradient Descent and Conflict Mitigation
par: Pan, Zibin, et autres
Publié: (2024)

Federated Learning with Relative Fairness
par: Nakakita, Shogo, et autres
Publié: (2024)

Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality
par: Wei, Ziyang, et autres
Publié: (2023)