AI & ML
Maximal Inequalities for Empirical Processes under General Mixing Conditions
arXiv stat.TH0 views
arXiv:2402.11394v5 Announce Type: replace-cross Abstract: This paper provides a bound for the supremum of sample averages over a class of functions for a general class of mixing stochastic processes with arbitrary mixing rates. Regardless of the speed of mixing, the bound is comprised of a concentration rate and a novel measure of complexity. The speed of mixing, however, affects the former quantity implying a phase transition. Fast mixing leads to the standard root-n concentration rate, while slow mixing leads to a slower concentration rate whose speed depends on the mixing structure. Our findings are applied to obtain new Glivenko-Cantelli type results.
Source：https://arxiv.org/abs/2402.11394PreviousThe Geometry of Latent Spaces: Projective Invariants, Structural Identification, and Ratio-Scale MeasurementNextNon-Gaussian Uncertainty Estimation via Semi-nonparametric Density
Related posts
![Meta Learning and Few Shot Adaptation — Ch.01: Learning to Learn [KR]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2F4kowd0l7axlmeg8ofakf.png)
Meta Learning and Few Shot Adaptation — Ch.01: Learning to Learn [KR]
0dev.to
![Meta Learning and Few Shot Adaptation — Ch.02: MAML and Optimization Based Meta Learning [KR]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fi8snoe7gyt31ex7pvhpp.png)
Meta Learning and Few Shot Adaptation — Ch.02: MAML and Optimization Based Meta Learning [KR]
0dev.to
![Meta Learning and Few Shot Adaptation — Ch.03: Metric Based Few Shot Learning [KR]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fbmxigikl0zmtua3kwiu8.png)
Meta Learning and Few Shot Adaptation — Ch.03: Metric Based Few Shot Learning [KR]
0dev.to
![Meta Learning and Few Shot Adaptation — Ch.04: Fast Adaptation [KR]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2F26g0vvnyhgbzj9t7onrg.png)
Meta Learning and Few Shot Adaptation — Ch.04: Fast Adaptation [KR]
0dev.to
![Meta Learning and Few Shot Adaptation — Ch.05: Meta RL [KR]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2F32lkdno1nfbc8wdk4600.png)
Meta Learning and Few Shot Adaptation — Ch.05: Meta RL [KR]
0dev.to
![Meta Learning and Few Shot Adaptation — Ch.06: Generalization and Adaptation [KR]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fou8tbyyld435ajhkxmf4.png)
Meta Learning and Few Shot Adaptation — Ch.06: Generalization and Adaptation [KR]
0dev.to