Professional Documents
Culture Documents
1
Importance Weighting
2
Importance Weighting
3
Overview
Preliminaries
Learning guarantee when loss is bounded
Learning guarantee when loss is unbounded, but second moment
is bounded
Algorithm
4
Preliminaries: Rnyi divergence
( )1
1 P(x)
D (P||Q) = log2 P(x)
1 x
Q(x)
[ ] 1
1
P (x)
D (P||Q)
d (P||Q) = 2 =
x
Q1 (x)
5
Preliminaries: Importance weights
Lemma 1:
Proof:
( P(x) )2
2 2
EQ [w ] = w (x)Q(x) = Q(x) = d2 (P||Q)
Q(x)
xX xX
6
Preliminaries: Importance weights
1 1
Hlders Inequality (Jin, Wilson, and Nobel, 2014): Let p + q = 1, then
( ) p1 ( ) q1
p q
|ax bx | |ax | |bx |
x x x
7
Preliminaries: Importance weights
[ ]2 [ ]
2 P(x) 1 P(x) 1
ExQ [w (x)L2h (x)] = Q(x) L2h (x) = P(x) P(x) L2h (x)
x
Q(x) x
Q(x)
[ [ ] ] 1 [ ] 1
P(x) 2
P(x) P(x)Lh (x)
1
x
Q(x) x
[ +1
] 1
= d+1 (P||Q) P(x)Lh (x)Lh 1
(x)
x
1 1 1
d+1 (P||Q)R(h)1 B1+ = d+1 (P||Q)R(h)1
8
Learning Guarantees: Bounded case
P(x)
supx w(x) = supx Q(x) = d (P||Q) = M. Let d (P||Q) < +. Fix h H.
Then, for any > 0, with probability at least 1 ,
2
w (h)| M log
|R(h) R
2m
9
Overview
Preliminaries
Learning guarantee when loss is bounded
Learning guarantee when loss is unbounded, but second moment
is bounded
Algorithm
10
Learning Guarantees: Bounded case
11
Learning Guarantees: Bounded case
when |xi | M.
12
Learning Guarantees: Bounded case
( )
m2 /2
Pr[R(h) R
w (h) > ] exp .
2 (Z) + M/3
13
Learning Guarantees: Bounded case
1
w (h) + 2M log + 2 2 (Z) log 1
=R
3m m
14
Learning Guarantees: Bounded case
Theorem 2: Let H be a nite hypothesis set. Then for any > 0, with
probability at least 1 , the following holds for the importance
weighting method:
w (h) + 2M(log|H| + log ) + 2d2 (P||Q)(log |H| = log
1 1
R(h) R
3m m
15
Learning Guarantees: Bounded case
16
Learning Guarantees: Bounded case
17
Overview
Preliminaries
Learning guarantee when loss is bounded
Learning guarantee when loss is unbounded, but second moment
is bounded
Algorithm
18
Learning Guarantees: Unbounded case
19
Learning Guarantees: Unbounded case
20
Learning Guarantees: Unbounded case
21
Learning Guarantees: Unbounded case
22
Learning Guarantees: Unbounded case
24
Overview
Preliminaries
Learning guarantee when loss is bounded
Learning guarantee when loss is unbounded, but second moment
is bounded
Algorithm
25
Alternative algorithms
( ) p log 2me 4
p + log
3
+25/4 max
8
EQ [u2 (x)L2h (x)], EQ [u2 (x)L2h (x)]
m
26
Alternative algorithms
[ ]
minuU E |w(x u(x)| + EQ [u2 ]
Trade-off between bias and variance minimization.
27
Alternative algorithms
28
Alternative algorithms
29