A Proofs
–Neural Information Processing Systems
Fix some sufficiently large dimension d and integer m d to be chosen later. Where δ (0, 1) is a certain scaling factor and V is a 1-valued matrix of size n m, both to be chosen later. B. To that end, we let V be any 1-valued n m matrix Thus, we can shatter any number m of points up to this upper bound. A.2 Proof of Thm. 2 To simplify notation, we rewrite sup Considering this constraint in Eq. (6), we see that for any choice of ϵ, v and w To continue, it will be convenient to get rid of the absolute value in the displayed expression above. Considering Eq. (8), this is 2bB times the Rademacher complexity of the function class {x ψ(w In other words, this class is a composition of all linear functions of norm at most 1, and all univariate L-Lipschitz functions crossing the origin.
Neural Information Processing Systems
May-29-2025, 10:26:40 GMT
- Technology: