Multi-Observation Elicitation

نویسندگان

  • Sebastian Casalaina-Martin
  • Rafael M. Frongillo
  • Tom Morgan
  • Bo Waggoner
چکیده

We study loss functions that measure the accuracy of a prediction based on multiple data points simultaneously. To our knowledge, such loss functions have not been studied before in the area of property elicitation or in machine learning more broadly. As compared to traditional loss functions that take only a single data point, these multi-observation loss functions can in some cases drastically reduce the dimensionality of the hypothesis required. In elicitation, this corresponds to requiring many fewer reports; in empirical risk minimization, it corresponds to algorithms on a hypothesis space of much smaller dimension. We explore some examples of the tradeoff between dimensionality and number of observations, give some geometric characterizations and intuition for relating loss functions and the properties that they elicit, and discuss some implications for both elicitation and machine-learning contexts.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Design of a Hyper Media Tool to support Requirements Elicitation Meetings

In this paper, we introduce a hyper media tool for requirements elicitation meetings. We consider requirements elicitation meetings as a consensus making process among participants who have their own roles. Participants in the meeting usually repeat the following activities to finish the final specification; • Preparing agenda and/or final specification for the next meeting while referring both...

متن کامل

Constructing and Clearing Combinatorial Exchanges Using Preference Elicitation

Combinatorial exchanges arise naturally in multi-agent systems that execute hierarchically decomposed tasks, when the agents have uncertainty about each other’s tasks and each other’s capability of handling tasks. In a combinatorial exchange, the information is aggregated to one party who then decides the task allocation among the agents. Unfortunately, such exchanges can require that bidders c...

متن کامل

Imprecise Swing Weighting for Multi-Attribute Utility Elicitation Based on Partial Preferences

We describe a novel approach to multi-attribute utility elicitation which is both general enough to cover a wide range of problems, whilst at the same time simple enough to admit reasonably straightforward calculations. We allow both utilities and probabilities to be only partially specified, through bounding. We still assume marginal utilities to be precise. We derive necessary and sufficient ...

متن کامل

Sequential-Simultaneous Information Elicitation in Multi-Agent Systems

We introduce a general setting for information elicitation in multi-agent systems, where agents may be approached both sequentially and simultaneously in order to compute a function that depends on their private secrets. We consider oblivious mechanisms for sequential-simultaneous information elicitation. In such mechanisms the ordering of agents to be approached is fixed in advance. Surprising...

متن کامل

Construction of time preference : an investigation of the role of elicitation method in experimental elicitation of time preference

Abstract The idea of preference reversal and construction of preference is not new to literature in decision making. Indeed, several theories have been developed to explain it. (Lichtenstein and Slovic, 2006). The present paper considers heuristics activated in different elicitation procedures applied in time preference research. I show that activation of these rules in correspondence with diff...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017