2000 character limit reached
An Improved Uniform Convergence Bound with Fat-Shattering Dimension
Published 13 Jul 2023 in cs.LG and stat.ML | (2307.06644v1)
Abstract: The fat-shattering dimension characterizes the uniform convergence property of real-valued functions. The state-of-the-art upper bounds feature a multiplicative squared logarithmic factor on the sample complexity, leaving an open gap with the existing lower bound. We provide an improved uniform convergence bound that closes this gap.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.