← Authors

Jingfeng Wu

29 papers · 2019–2025 · 9 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (6) πŸ—ΊοΈ Taxonomy Completionist (12) 🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (7) 🌍 Conference Polyglot (9) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🀝 Dynamic Duo (17) πŸ—ƒοΈ Keyword Collector (111) ❓ The Questioner (3) ⚑ Prolific Year (6) πŸ’Ž Century Club (29) πŸ”₯ Unstoppable (7)

Conferences

NIPS (9) ICML (8) ICLR (4) COLT (2) NSDI (2) ACML (1) AISTATS (1) CVPR (1) JMLR (1)

Top co-authors

Vladimir braverman (17) Difan Zou (10) Quanquan Gu (10) Sham Kakade (5) Peter Bartlett (4) Peter L. Bartlett (4) Sham M. Kakade (4) Zhanxing Zhu (3) Lin Yang (3) Jinwen Ma (2)

Research topics

Optimization (1) Differential Privacy (1)

Keywords

stochastic gradient descent (8) linear regression (5) gradient descent (4) excess risk (3) iterate averaging (3) logistic regression (2) learning theory (2) risk bound (2) neural network optimization (2) overparameterized learning (2) implicit bia (2) catastrophic forgetting (1) domain adaptation (1) manifold regularization (1) transfer learning (1) neural tangent kernel (1) stochastic optimization (1) model selection (1) sample complexity (1) iterative optimization (1)

Papers

Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes ICML 2025
Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression ICML 2025
Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks ICML 2025
How Does Critical Batch Size Scale in Pre-training? ICLR 2025
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization NIPS 2024
Scaling Laws in Linear Regression: Compute, Parameters, and Data NIPS 2024
Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency COLT 2024
Risk Bounds of Accelerated SGD for Overparameterized Linear Regression ICLR 2024
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization NIPS 2024
How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? ICLR 2024
Benign Overfitting of Constant-Stepsize SGD for Linear Regression JMLR 2023
Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron ICML 2023
Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability NIPS 2023
Private Federated Frequency Estimation: Adapting to the Hardness of the Instance NIPS 2023
Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression ICML 2022
Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime NIPS 2022
Gap-Dependent Unsupervised Exploration for Reinforcement Learning AISTATS 2022
The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift NIPS 2022
Ship Compute or Ship Data? Why Not Both? NSDI 2021
Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning NIPS 2021
Lifelong Learning with Sketched Structural Regularization ACML 2021
Benign Overfitting of Constant-Stepsize SGD for Linear Regression COLT 2021
Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate ICLR 2021
Twenty Years After: Hierarchical Core-Stateless Fair Queueing NSDI 2021
The Benefits of Implicit Regularization from SGD in Least Squares Problems NIPS 2021
On the Noisy Gradient Descent that Generalizes as SGD ICML 2020
Obtaining Adjustable Regularization for Free via Iterate Averaging ICML 2020
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects ICML 2019
Tangent-Normal Adversarial Regularization for Semi-Supervised Learning CVPR 2019