日本語
 
Help Privacy Policy ポリシー/免責事項
  詳細検索ブラウズ

アイテム詳細

  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

基本情報

表示: 非表示:
アイテムのパーマリンク: https://hdl.handle.net/21.11116/0000-000A-9932-1 版のパーマリンク: https://hdl.handle.net/21.11116/0000-000A-993C-7
資料種別: 成果報告書

ファイル

表示: ファイル
非表示: ファイル
:
arXiv:2201.12006.pdf (プレプリント), 2MB
ファイルのパーマリンク:
https://hdl.handle.net/21.11116/0000-000A-9934-F
ファイル名:
arXiv:2201.12006.pdf
説明:
File downloaded from arXiv at 2022-06-15 13:49
OA-Status:
閲覧制限:
公開
MIMEタイプ / チェックサム:
application/pdf / [MD5]
技術的なメタデータ:
著作権日付:
-
著作権情報:
-

関連URL

表示:

作成者

表示:
非表示:
 作成者:
Straitouri, Eleni1, 著者
Wang, Lequn2, 著者
Okati, Nastaran1, 著者           
Gomez Rodriguez, Manuel1, 著者           
所属:
1Group M. Gomez Rodriguez, Max Planck Institute for Software Systems, Max Planck Society, ou_2105290              
2External Organizations, ou_persistent22              

内容説明

表示:
非表示:
キーワード: Computer Science, Learning, cs.LG,Computer Science, Computers and Society, cs.CY,Computer Science, Human-Computer Interaction, cs.HC,Statistics, Machine Learning, stat.ML
 要旨: 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.

資料詳細

表示:
非表示:
言語: eng - English
 日付: 2022-01-282022-05-232022
 出版の状態: オンラインで出版済み
 ページ: 16 p.
 出版情報: -
 目次: -
 査読: -
 識別子(DOI, ISBNなど): arXiv: 2201.12006
URI: https://arxiv.org/abs/2201.12006
BibTex参照ID: Straitouri2022
 学位: -

関連イベント

表示:

訴訟

表示:

Project information

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

出版物

表示: