Learning from Low Rank Tensor Data: A Random Tensor Theory Perspective - UAI 2023 Oral Session 4

Explore a 22-minute conference talk from the Uncertainty in Artificial Intelligence (UAI) 2023 Oral Session 4 that delves into learning from low-rank tensor data through a random tensor theory perspective. Gain insights into the theoretical analysis of both supervised and unsupervised learning scenarios using simplified data models with underlying low-rank tensor structures. Discover the analytical quantification of performance gains achieved by exploiting low-rank structures for denoising in Ridge classification, compared to treating data as vectors. Examine the extension of this analysis to clustering contexts, understanding the exact performance differences between tensor methods and standard vector-based approaches. Access the presentation slides to enhance your comprehension of this cutting-edge research in machine learning and data analysis.

UAI 2023 Oral Session 4: Learning from Low Rank Tensor Data: A Random Tensor Theory Perspective