Cover Image

Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Jingfeng, Bartlett, Peter L., Telgarsky, Matus, Yu, Bin
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

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
by: Wu, Jingfeng, et al.
Published: (2025)

Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
by: Wu, Jingfeng, et al.
Published: (2025)

Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
by: Zhang, Ruiqi, et al.
Published: (2025)

Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
by: Cai, Yuhang, et al.
Published: (2024)

Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension
by: Crawshaw, Michael, et al.
Published: (2026)

Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks
by: Cai, Yuhang, et al.
Published: (2025)

On Achieving Optimal Adversarial Test Error
by: Li, Justin D., et al.
Published: (2023)

Transformers, parallel computation, and logarithmic depth
by: Sanford, Clayton, et al.
Published: (2024)

One-layer transformers fail to solve the induction heads task
by: Sanford, Clayton, et al.
Published: (2024)

Improved Scaling Laws in Linear Regression via Data Reuse
by: Lin, Licong, et al.
Published: (2025)

Gradient Descent on Logistic Regression with Non-Separable Data and Large Step Sizes
by: Meng, Si Yi, et al.
Published: (2024)

Negative Stepsizes Make Gradient-Descent-Ascent Converge
by: Shugart, Henry, et al.
Published: (2025)

Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent
by: Li, Xiang, et al.
Published: (2024)

Astral Space: Convex Analysis at Infinity
by: Dudík, Miroslav, et al.
Published: (2022)

Conformal Risk Control for Non-Monotonic Losses
by: Angelopoulos, Anastasios N.
Published: (2026)

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
by: Schliserman, Matan, et al.
Published: (2025)

Lai Loss: A Novel Loss for Gradient Control
by: Lai, YuFei
Published: (2024)

Spectrum Extraction and Clipping for Implicitly Linear Layers
by: Boroojeny, Ali Ebrahimpour, et al.
Published: (2024)

Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
by: Sakaue, Shinsaku, et al.
Published: (2024)

In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization
by: Zhang, Ruiqi, et al.
Published: (2024)

Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis
by: Paik, Seunghoon, et al.
Published: (2025)

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
by: Frei, Spencer, et al.
Published: (2022)

Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses
by: Bao, Han, et al.
Published: (2025)

Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability
by: Crawshaw, Michael, et al.
Published: (2025)

From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes
by: Tyurin, Alexander
Published: (2024)

Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization
by: Wu, Jingfeng, et al.
Published: (2025)

Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential
by: Zheng, Yuping, et al.
Published: (2025)

Classification with Deep Neural Networks and Logistic Loss
by: Zhang, Zihan, et al.
Published: (2023)

AYLA: Amplifying Gradient Sensitivity via Loss Transformation in Non-Convex Optimization
by: Keslaki, Ben
Published: (2025)

Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
by: Vastola, John J., et al.
Published: (2025)

Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
by: Cattaneo, Matias D., et al.
Published: (2025)

An Improved Empirical Fisher Approximation for Natural Gradient Descent
by: Wu, Xiaodong, et al.
Published: (2024)

The Space Complexity of Approximating Logistic Loss
by: Dexter, Gregory, et al.
Published: (2024)

Conformal Risk Control under Non-Monotone Losses: Theory and Finite-Sample Guarantees
by: Aldirawi, Tareq, et al.
Published: (2026)

Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere?
by: Meng, Si Yi, et al.
Published: (2025)

MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes
by: Sokolov, Igor, et al.
Published: (2024)

Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression
by: Kale, Sacchit, et al.
Published: (2026)

An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes
by: Orvieto, Antonio, et al.
Published: (2024)

Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent
by: Zhang, Chenyang, et al.
Published: (2026)

Reinforcement Learning in POMDP's via Direct Gradient Ascent
by: Baxter, Jonathan, et al.
Published: (2025)