2000 character limit reached
On the Dimension-Free Concentration of Simple Tensors via Matrix Deviation (2506.09333v2)
Published 11 Jun 2025 in math.PR
Abstract: We provide a simpler proof of a sharp concentration inequality for subgaussian simple tensors obtained recently by Al-Ghattas, Chen and Sanz-Alonso. Our approach uses a matrix deviation inequality for $\ellp$ norms and a basic chaining argument.