We first state a generic inequality based on Lemma 2. This differs from earlier approaches, which instead combine Markov’s inequality with a result similar to Lemma 2 (e.g., Tropp, 2011a, Theorem 3.6).
In this work, we have provided deterministic inequalities for a class of smooth M-estimators that unify the classical asymptotic analysis under various dependence settings. Furthermore, these inequalities readily yield tail bounds for estimation err…
There aren't more papers