Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Peng Zhao

Peng Zhao

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

ML×3Stats ML×3AI×1Stats Theory×1

Frequent co-authors

Yan-Feng Xie2×
Shuche Wang2×
Zhi-Hua Zhou2×
Yifei Sun1×
Le Zhang1×
Bingjin Chen1×

Research Timeline

2026
Online Learning with Gradient-Variation Interval Regret

The paper proposes a novel online learning algorithm that achieves an interval regret bound scaling with gradient variation, providing strong theoretical guarantees for non-stationary environments.

Online Learning with Gradient-Variation Interval Regret

The paper proposes a novel online learning algorithm that achieves an interval regret bound scaling with gradient variation, providing strong theoretical guarantees for non-stationary environments.

Beyond Negative-Ridge Endpoints: Mixed-Sign Spectral Regularization via Negative-Shifted Gradient Descent

This paper proposes a method for handling overparameterized linear regression using early-stopped negative-shifted gradient descent, which allows for smooth filters and mixed-sign capabilities.

WebViSE: Scaling Visual Design Intelligence from the Open Web for LLM Website Generation

This paper introduces WebViSE, a framework that extracts reusable visual skills from existing websites and uses them to improve the visual quality and interaction fidelity of website-building models.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentOct 24, 2026

WebViSE: Scaling Visual Design Intelligence from the Open Web for LLM Website Generation

Yifei Sun, Peng Zhao, Le Zhang, Bingjin Chen +1 more

This paper introduces WebViSE, a framework that extracts reusable visual skills from existing websites and uses them to improve the visual quality and interaction fidelity of website-building models.

View →
cs.LGmath.STstat.MLTheoretical
Recent
Jul 24, 2026

Beyond Negative-Ridge Endpoints: Mixed-Sign Spectral Regularization via Negative-Shifted Gradient Descent

Peng Zhao

This paper proposes a method for handling overparameterized linear regression using early-stopped negative-shifted gradient descent, which allows for smooth filters and mixed-sign capabilities.

View →
cs.LGstat.MLRecentJun 2, 2026

Online Learning with Gradient-Variation Interval Regret

Yan-Feng Xie, Shuche Wang, Peng Zhao, Zhi-Hua Zhou

The paper proposes a novel online learning algorithm that achieves an interval regret bound scaling with gradient variation, providing strong theoretical guarantees for non-stationary environments.

View →
cs.LGstat.MLRecentJun 2, 2026

Online Learning with Gradient-Variation Interval Regret

Yan-Feng Xie, Shuche Wang, Peng Zhao, Zhi-Hua Zhou

The paper proposes a novel online learning algorithm that achieves an interval regret bound scaling with gradient variation, providing strong theoretical guarantees for non-stationary environments.

View →