Mark Herbster
Papers
1
Total Citations
16
H-Index
1
About
Mark Herbster is a leading researcher in machine learning theory, with a particular focus on online learning, kernel methods, and the emerging intersection of quantum computing with artificial intelligence. His work bridges foundational theory and practical applications, notably in computer vision, where he has explored how quantum pre-training and auto-encoders can enhance image classification—a contribution that has garnered 16 citations and opened new avenues for near-term quantum advantages. Herbster’s broader impact is reflected in his highly cited papers on prediction with expert advice and graph-based learning, which have shaped modern online learning algorithms. He is also recognized for his work on learning with limited memory and adaptive algorithms, addressing critical challenges in resource-constrained environments. With a career spanning influential contributions to both theoretical and applied machine learning, Herbster’s research continues to inspire students and researchers seeking to understand the limits and possibilities of learning systems in complex, dynamic settings.
Research Focus
Key Achievements
Top Papers
- 1Image classification with quantum pre-training and auto-encoders16 citations · 2018