On the Relation between Robust and Bayesian Decision Making



3 Linking Bayesian and Robust Decision Prob-
lems

The objective of this section is to establish a link between the Bayesian and the
robust decision problems described in the previous section. The main idea is to
change the objective function of the Bayesian decision problem in a way that
the Bayesian’s objective will have the same minimum as the robust objective.

Since the Bayesian’s loss function depends on the action x, altering the loss
function is a back-door through which one can cause the Bayesian to behave as
if her priors were changing across actions. In particular, if the Bayesian was to
maximize a transformed loss function
T(L(x,s)) with the property that

T(L(x, s)) = L(x, s) ——-,-—ɪ                         (5)

Ps

where ps is the prior probability for state s, then the Bayesian problem would
be identical to the robust decision problem:

min E [T(L(x, s))]

nΩ1

= min ^ L(x,si)1 (x,Sl)pi
^Ωs ,                  pi

i=l

= min R(x)
xΩx

Of course, such a transformed ’loss function’ is not a loss function in the strict
sense since it depends on prior probabilities.

Given that direct equivalence between the two problems requires a Bayesian
loss that depends on priors, the strategy is to construct a sequence of trans-
formed loss functions
Tk(L(x,s)) for the Bayesian problem with the property
that these transformed loss functions are
independent of the prior. At the same
time the solution to

min E [Tk(L(x, s))]                            (6)

ω

which is denoted by x*k should converge to the robust solution x* as к increases
without bound, i.e.

jɪɪɪɪ ιxk -x* и =°.

k→∞



More intriguing information

1. The name is absent
2. Income Growth and Mobility of Rural Households in Kenya: Role of Education and Historical Patterns in Poverty Reduction
3. The name is absent
4. The name is absent
5. The name is absent
6. Text of a letter
7. The name is absent
8. PERFORMANCE PREMISES FOR HUMAN RESOURCES FROM PUBLIC HEALTH ORGANIZATIONS IN ROMANIA
9. The name is absent
10. The name is absent