Processing math: 42%

Welcome to Randal Douc's wiki

A collaborative site on maths but not only!

User Tools

Site Tools


world:optimal-classifier

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
world:optimal-classifier [2023/11/04 12:20]
rdouc
world:optimal-classifier [2023/11/04 14:03] (current)
rdouc [Bayes Optimal Classifier]
Line 9: Line 9:
 where F is the set of measurable functions from \rsetk to [1:p] where we equip \rsetk with the σ-field \mcbb(\rsetk) and [1:p] with the σ-field \mc{P}([1:​p]). ​ where \sf{F} is the set of measurable functions from \rset^k to [1:p] where we equip \rset^k with the \sigma-field \mcbb(\rset^k) and [1:p] with the \sigma-field \mc{P}([1:​p]). ​
  
-<WRAP center round tip 80%> +<WRAP center round tip 90%> 
-**__Proposition__**.  ​+**__Proposition__** ​
 $$ $$
 \inf_{\phi \in \sf{F}} \PP(Y\neq \phi(X))= \PE\lrb{\min_{i \in [1:p]} \PP(Y \neq i|X)}=\PP(Y \neq \phi^\star(X)) \inf_{\phi \in \sf{F}} \PP(Y\neq \phi(X))= \PE\lrb{\min_{i \in [1:p]} \PP(Y \neq i|X)}=\PP(Y \neq \phi^\star(X))
Line 28: Line 28:
 \phi^\star(X)= \argmin_{i \in [1:p]} \PP(Y \neq i|X)=\argmax_{i \in [1:p]} \PP(Y=i|X) \phi^\star(X)= \argmin_{i \in [1:p]} \PP(Y \neq i|X)=\argmax_{i \in [1:p]} \PP(Y=i|X)
 $$ $$
-which concludes the proof. ​+where the last equality follows from the identity \PP(Y \neq i|X)=1-\PP(Y=i|X). This concludes the proof. ​
world/optimal-classifier.1699096847.txt.gz · Last modified: 2023/11/04 12:20 by rdouc