Bayes Risk Minimum Expected Loss

Problem

Given class posteriors and a 2x2 loss matrix (rows are actions, columns are true classes), the Bayes risk is the minimum over actions of sum_j posterior_j loss[a][j].

Given the posteriors and the loss matrix, return the Bayes risk.

Hint

Evaluate every action and take the smallest expected loss.

Test cases

case 1

in: [[0.7,0.3],[[0,1],[1,0]]]

expected: 0.3

case 2

in: [[0.7,0.3],[[0,5],[1,0]]]

expected: 0.7

case 3

in: [[0.5,0.5],[[2,2],[2,2]]]

expected: 2

Starter codePython

def bayes_risk_minimum_expected_loss(posteriors, loss_matrix):
    # Your code here
    pass

3 test cases · run your code against them in the editor