Together, these two results suggest a number of new open problems for future work: What is the underlying mechanism that p > 1 can lead to a better noiseless recovery?
Statement
Together, these two results suggest a number of new open problems for future work: What is the underlying mechanism that p > 1 can lead to a better noiseless recovery? Could this regularized max-average-margin estimator achieve the optimal O(1/n) rate in the noiseless \sqrt{ } case, while interpolating max- margin interpolators can only achieve O(1/ n)? Surprising phenomena of max-ℓp -margin classifiers in high dimensions Fanny Yang
Record
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.