A Mosco sufficient condition for intrinsic stability of non-unique convex Empirical Risk Minimization
Empirical risk minimization (ERM) stability is usually studied via single-valued outputs, while convex non-strict losses yield set-valued minimizers. We identify Painlevé-Kuratowski upper semicontinuity (PK-u.s.c.) as the intrinsic stability notion for the ERM solution correspondence (set-level Hadamard well-posedness) and a prerequisite to interpret stability of selections. We then characterize a minimal non-degenerate qualitative regime: Mosco-consistent perturbations and locally bounded minimizers imply PK-u.s.c., minimal-value continuity, and consistency of vanishing-gap near-minimizers. Quadratic growth yields explicit quantitative deviation bounds.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Stability of Equilibrium Asset Pricing Models: A Necessary and Sufficient Condition
We obtain an exact necessary and sufficient condition for the existence and uniqueness of equilibrium asset prices in infinite horizon, discrete-time, arbitrage free environments. Through several applications we show how…
Conditions for none to be whipped by `Rank and Yank' under the majority rule
`Rank and Yank' is practiced in many organizations. This paper is concerned with the condtions for none to be whipped by `Rank and Yank' when the evaluation data under each criterion are assumed to be ordinal rankings an…
Homogeneity of Cluster Ensembles
The expectation and the mean of partitions generated by a cluster ensemble are not unique in general. This issue poses challenges in statistical inference and cluster stability. In this contribution, we state sufficient …
ClusteringDiversityA sufficient condition for $k$-contraction in Lurie systems
We consider a Lurie system obtained via a connection of a linear time-invariant system and a nonlinear feedback function. Such systems often have more than a single equilibrium and are thus not contractive with respect t…
LEMMAPrioritized Inverse Kinematics: Desired Task Trajectories in Nonsingular Task Spaces
A prioritized inverse kinematics (PIK) solution can be considered as a (regulation or output tracking) control law of a dynamical system with prioritized multiple outputs. We propose a method that guarantees that a joint…