← Search

Peijia Li

2 accepted papers

2025

Dimension-Free Adaptive Subgradient Methods with Frequent Directions

ICML 2025poster

In this paper, we investigate the acceleration of adaptive subgradient methods through frequent directions (FD), a widely-used matrix sketching technique. The state-of-the-art regret bound exhibits a _linear_ dependence on the dimensionality $d$, leading to unsatisfactory guarantees for high-dimensi…

Cited by 0SourcePDFScholar
2025

Reinforcement Learning-Guided Data Selection via Redundancy Assessment

ICCV 2025poster

Modern deep architectures often rely on large-scale datasets, but training on these datasets incurs high computational and storage overhead. Real-world datasets often contain substantial redundancies, prompting the need for more data-efficient training paradigms. Data selection has shown promise to…

Cited by 0SourcePDFScholar