Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration bounds
1 directory member surfaced this signal.
“From my point of view, the objective is close to my previous paper with V. Karagulyan and M. Kasprzak: arxiv.org/abs/2610.20007 we want deviation bounds that can be used to define agnostic learning objectives. What differs here is 1) the class of processes …” evidence ↗
“From my point of view, the objective is close to my previous paper with V. Karagulyan and M. Kasprzak: arxiv.org/abs/2610.20007 we want deviation bounds that can be used to define agnostic learning objectives. What differs here is 1) the class of processes …”