# Questions tagged [convergence]

Convergence generally means that a sequence of a certain sample quantity approaches a constant as the sample size tends to infinity. Convergence is also a property of an iterative algorithm to stabilize on some aim value.

804 questions
Filter by
Sorted by
Tagged with
13 views

### Neural network training converges for several epochs, then diverges badly

I have a VGG-like network that I have trained from scratch on a multi-class dataset of my own. The results suggested there were probably some data errors somewhere, so I thought I would train the same ...
15 views

### What's the relationship between these two statements?

Suppose I have a set $A\subset R^2$ and an estimator for set $A$ denoted as $\widehat{A}$. Let $\widehat{A}\Delta A$ denote the symmetric difference between set $\widehat{A}$ and set $A$. For some ...
36 views

35 views

59 views

45 views

### Question on Convergence in distribution

Belyaev and Sjöstedt-de Luna introduced the notion of weakly approaching sequences of distributions, generalizing the weak convergence without imposing the limiting distribution. Definition. Two ...
30 views

49 views

### What makes MCMC converge?

Here is what I have learned about MCMC recently 1) We first propose a likelihood function that describes our problem (Binomial) 2) We define a conjugate prior (Beta) and posterior distribution (Beta-...
53 views

### How can these two expressions both converge in distribution to N(0, 1)?

In All of Statistics, chapter 11 (pg. 183), Larry Wasserman states in his description of the Wald Test: We are testing the null hypothesis $\hat{\theta} = \theta_0$ versus the alternative ...