Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition

Published in IJCAI, 2025

FORKS is a fast, incremental matrix sketching and decomposition approach for OKL that improves scalability, reduces time complexity to linear, and maintains strong regret guarantees, outperforming existing methods in real-world streaming recommender systems.

Download Paper

Optimal Matrix Sketching over Sliding Windows

Published in VLDB, 2024

This paper introduces the DSFD algorithm, which achieves optimal space bounds for matrix sketching over sliding windows, answering the open question on efficient space usage in this context.

Download Paper

Dongxie Wen

Publications

Conference Papers

Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition

Optimal Matrix Sketching over Sliding Windows