en
0.25
0.5
0.75
1.25
1.5
1.75
2
Complexity-Based Approach to Calibration with Checking Rules
Published on Aug 02, 20113479 Views
We consider the problem of forecasting a sequence of outcomes from an unknown source. The quality of the forecaster is measured by a family of checking rules. We prove upper bounds on the value of the
Related categories
Chapter list
Complexity-Based Approach to Calibration with Checking Rules00:00
Calibration00:45
A Must-Have Slide - 102:10
A Must-Have Slide - 202:43
Calibration for individual sequences - 102:51
Calibration for individual sequences - 203:15
Calibration for individual sequences - 303:31
Calibration for individual sequences - 404:02
Why calibration?04:22
Why introduce checking rules?? - 105:28
Why introduce checking rules?? - 205:40
Why introduce checking rules?? - 305:55
Why introduce checking rules?? - 406:16
Why introduce checking rules?? - 506:36
Setup - 107:55
Setup - 207:56
Setup - 307:59
Setup - 408:14
Setup - 508:33
Setup - 609:03
Examples - 111:01
Examples - 211:04
Examples - 311:55
Value of the Game13:04
Main Results - 114:07
Main Results - 214:08
Main Results - 315:38
Main Results - 415:39
Main Results - 516:04
Families of checking rules - 116:12
Families of checking rules - 216:16
Families of checking rules - 316:35
Families of checking rules - 417:00
Families of checking rules - 517:32
More families of checking rules18:09
A lower bound19:10
A few remarks - 119:19
A few remarks - 220:13
Future work20:36