Machine learning is most often cast as an optimization problem. Ideally, one expects a convex objective function to rely on efficient convex optimizers with nice guarantees such as no local optima. Yet, non-convexity is very frequent in practice and it may ...
We study continuity properties of law-invariant (quasi-)convex functions f : L1(Ω,F, P) to ( ∞,∞] over a non-atomic probability space (Ω,F, P) .This is a supplementary note to [12] ...
In this paper we find properties that are shared between two seemingly unrelated lossy source coding setups with side-information. The first setup is when the source and side-information are jointly Gaussian and the distortion measure is quadratic. The sec ...
Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2009