Cover Image

Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yoshida, Naoki, Nakakita, Shogo, Imaizumi, Masaaki
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

Benign Overfitting in Time Series Linear Models with Over-Parameterization
by: Nakakita, Shogo, et al.
Published: (2022)

Federated Learning with Relative Fairness
by: Nakakita, Shogo, et al.
Published: (2024)

Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry
by: Yoshida, Naoki, et al.
Published: (2025)

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
by: Chen, Baiyuan, et al.
Published: (2025)

Non-asymptotic analysis of Langevin-type Monte Carlo algorithms
by: Nakakita, Shogo
Published: (2023)

Dimension-free Bounds for Sum of Dependent Matrices and Operators with Heavy-Tailed Distribution
by: Nakakita, Shogo, et al.
Published: (2022)

Sharp concentration of uniform generalization errors in binary linear classification
by: Nakakita, Shogo
Published: (2025)

On sample complexity for covariance estimation via the unadjusted Langevin algorithm
by: Nakakita, Shogo
Published: (2026)

Dimension-free uniform concentration bound for logistic regression
by: Nakakita, Shogo
Published: (2024)

Approximation of Permutation Invariant Polynomials by Transformers: Efficient Construction in Column-Size
by: Takeshita, Naoki, et al.
Published: (2025)

High-dimensional Nonparametric Contextual Bandit Problem
by: Iwazaki, Shogo, et al.
Published: (2025)

Effect of Weight Quantization on Learning Models by Typical Case Analysis
by: Kashiwamura, Shuhei, et al.
Published: (2024)

Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality
by: Tamano, Shu, et al.
Published: (2026)

Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
by: Nishiyama, Sota, et al.
Published: (2025)

Neuron Block Dynamics for XOR Classification with Zero-Margin
by: Braun, Guillaume, et al.
Published: (2026)

Bayesian Analysis for Over-parameterized Linear Model via Effective Spectra
by: Wakayama, Tomoya, et al.
Published: (2023)

High-Dimensional Limit of Stochastic Gradient Flow via Dynamical Mean-Field Theory
by: Nishiyama, Sota, et al.
Published: (2026)

Minimax Rates of Estimation for Optimal Transport Map between Infinite-Dimensional Spaces
by: Ponnoprat, Donlapark, et al.
Published: (2025)

Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
by: Sakai, Mana, et al.
Published: (2025)

High-dimensional Contextual Bandit Problem without Sparsity
by: Komiyama, Junpei, et al.
Published: (2023)

Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers
by: Sakai, Mana, et al.
Published: (2026)

Near-Optimal Algorithm for Non-Stationary Kernelized Bandits
by: Iwazaki, Shogo, et al.
Published: (2024)

Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates
by: Kovalev, Dmitry, et al.
Published: (2025)

Automatic Domain Adaptation by Transformers in In-Context Learning
by: Hataya, Ryuichiro, et al.
Published: (2024)

Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent
by: Imai, Shota, et al.
Published: (2026)

Online Non-Stationary Stochastic Quasar-Convex Optimization
by: Pun, Yuen-Man, et al.
Published: (2024)

Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance
by: Iwazaki, Shogo, et al.
Published: (2025)

Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data
by: Braun, Guillaume, et al.
Published: (2025)

Finite-Sample Inference for Sparsely Permuted Linear Regression
by: Ota, Hirofumi, et al.
Published: (2026)

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization
by: Armacki, Aleksandar, et al.
Published: (2026)

Learning a Single Index Model from Anisotropic Data with vanilla Stochastic Gradient Descent
by: Braun, Guillaume, et al.
Published: (2025)

Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables
by: Imaizumi, Masaaki, et al.
Published: (2026)

SLowcal-SGD: Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
by: Dahan, Tehila, et al.
Published: (2023)

A Modular Algorithm for Non-Stationary Online Convex-Concave Optimization
by: Meng, Qing-xin, et al.
Published: (2025)

The Computational Complexity of Finding Stationary Points in Non-Convex Optimization
by: Hollender, Alexandros, et al.
Published: (2023)

Precise gradient descent training dynamics for finite-width multi-layer neural networks
by: Han, Qiyang, et al.
Published: (2025)

Iteration and Stochastic First-order Oracle Complexities of Stochastic Gradient Descent using Constant and Decaying Learning Rates
by: Imaizumi, Kento, et al.
Published: (2024)

Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees
by: Jin, Richeng, et al.
Published: (2020)

Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration
by: Khaled, Ahmed, et al.
Published: (2025)

Risk-averse Learning with Non-Stationary Distributions
by: Wang, Siyi, et al.
Published: (2024)