English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Provably Improving Expert Predictions with Prediction Sets

Straitouri, E., Wang, L., Okati, N., & Gomez Rodriguez, M. (2022). Provably Improving Expert Predictions with Prediction Sets. Retrieved from https://arxiv.org/abs/2201.12006.

Item is

Files

show Files
hide Files
:
arXiv:2201.12006.pdf (Preprint), 2MB
Name:
arXiv:2201.12006.pdf
Description:
File downloaded from arXiv at 2022-06-15 13:49
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Straitouri, Eleni1, Author
Wang, Lequn2, Author
Okati, Nastaran1, Author           
Gomez Rodriguez, Manuel1, Author           
Affiliations:
1Group M. Gomez Rodriguez, Max Planck Institute for Software Systems, Max Planck Society, ou_2105290              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: Computer Science, Learning, cs.LG,Computer Science, Computers and Society, cs.CY,Computer Science, Human-Computer Interaction, cs.HC,Statistics, Machine Learning, stat.ML
 Abstract: Automated decision support systems promise to help human experts solve tasks
more efficiently and accurately. However, existing systems typically require
experts to understand when to cede agency to the system or when to exercise
their own agency. Moreover, if the experts develop a misplaced trust in the
system, their performance may worsen. In this work, we lift the above
requirement and develop automated decision support systems that, by design, do
not require experts to understand when to trust them to provably improve their
performance. To this end, we focus on multiclass classification tasks and
consider an automated decision support system that, for each data sample, uses
a classifier to recommend a subset of labels to a human expert. We first show
that, by looking at the design of such a system from the perspective of
conformal prediction, we can ensure that the probability that the recommended
subset of labels contains the true label matches almost exactly a target
probability value. Then, we develop an efficient and near-optimal search method
to find the target probability value under which the expert benefits the most
from using our system. Experiments on synthetic and real data demonstrate that
our system can help the experts make more accurate predictions and is robust to
the accuracy of the classifier it relies on.

Details

show
hide
Language(s): eng - English
 Dates: 2022-01-282022-05-232022
 Publication Status: Published online
 Pages: 16 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 2201.12006
URI: https://arxiv.org/abs/2201.12006
BibTex Citekey: Straitouri2022
 Degree: -

Event

show

Legal Case

show

Project information

show hide
Project name : HumanML
Grant ID : 945719
Funding program : Horizon 2020 (H2020)
Funding organization : European Commission (EC)

Source

show