Sample-Efficient Active Learning from Human Feedback
Event details
| Date | 07.01.2026 |
| Hour | 11:15 › 12:00 |
| Speaker | Belen Martin-Urcelay, PhD Giorgia Tech, USA |
| Location | |
| Category | Conferences - Seminars |
| Event Language | English |
Abstract
Aligning machine learning systems with human intent requires querying experts, but collecting high-quality feedback at scale is often prohibitively expensive. This talk presents active learning frameworks designed to minimize sample complexity by exploiting structure in the data and the feedback mechanism.
The talk focuses on linear classifier learning within pre-trained embedding spaces. While traditional methods rely on simple labeling, we demonstrate that leveraging the embedding geometry allows for richer forms of feedback, such as rankings. We analyze how these richer queries theoretically reduce sample complexity. We further develop active learning strategies that explicitly balance informational value against annotation costs, leading empirically to significant cost reductions. The talk concludes by pointing out future avenues for more efficient human-in-the-loop learning.
Biography
Belén Martín-Urcelay is a Ph.D. candidate at Georgia Tech, advised by Matthieu Bloch and Christopher Rozell. She earned her B.Sc. and M.Sc. in Telecommunications Engineering from Universidad de Navarra before joining Georgia Tech for her doctorate. Her research focuses on active learning, human feedback, and reinforcement learning, with an emphasis on leveraging knowledgeable teachers (whether human experts or powerful machine learning models) to enhance learning algorithm performance. She has collaborated internationally, including a research visit to ETH Zurich with Andreas Krause. Outside of research, she is passionate about teaching, mentoring students, and promoting women in STEM fields.
Aligning machine learning systems with human intent requires querying experts, but collecting high-quality feedback at scale is often prohibitively expensive. This talk presents active learning frameworks designed to minimize sample complexity by exploiting structure in the data and the feedback mechanism.
The talk focuses on linear classifier learning within pre-trained embedding spaces. While traditional methods rely on simple labeling, we demonstrate that leveraging the embedding geometry allows for richer forms of feedback, such as rankings. We analyze how these richer queries theoretically reduce sample complexity. We further develop active learning strategies that explicitly balance informational value against annotation costs, leading empirically to significant cost reductions. The talk concludes by pointing out future avenues for more efficient human-in-the-loop learning.
Biography
Belén Martín-Urcelay is a Ph.D. candidate at Georgia Tech, advised by Matthieu Bloch and Christopher Rozell. She earned her B.Sc. and M.Sc. in Telecommunications Engineering from Universidad de Navarra before joining Georgia Tech for her doctorate. Her research focuses on active learning, human feedback, and reinforcement learning, with an emphasis on leveraging knowledgeable teachers (whether human experts or powerful machine learning models) to enhance learning algorithm performance. She has collaborated internationally, including a research visit to ETH Zurich with Andreas Krause. Outside of research, she is passionate about teaching, mentoring students, and promoting women in STEM fields.
Practical information
- General public
- Free