Predicting the Unpredictable

Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=YP2rUnKWABg



Duration: 1:01:20
407 views
7


This is a survey of results about the accuracy of prediction when the predictor has no prior knowledge about the process that s/he must forecast. No prior knowledge means just that; no information about moments, distributions, periods etc. For example, suppose one is asked to predict successive outcomes of an infinite sequence of 0's and 1's. Accuracy will be measured by the fraction of correct guesses. With no information beyond this, how well can one guarantee to do? Predicting the actual outcome is demanding and in many cases inappropriate; think for example of the case when the sequence is generated by a stochastic process. In these cases it is more natural to ask for a probability forecast. How should one measure the error of a probability forecast? Given this measure, are there forecasting methods that guarantee a small error no matter what process generates the sequence?




Other Videos By Microsoft Research


2016-09-05SSCLI RFP II Capstone Workshop ΓÇô Flexible Dynamic Linking for .NET
2016-09-05SpeechPad: Multimodal Text Entry on Mobile Devices
2016-09-05SSCLI RFP II Capstone Workshop - Traits in C#
2016-09-05An Empirical Analysis of Rate Limiting Mechanisms to Contain Internet Worms
2016-09-05Extending Rotor with Structural Reflection to Support Reflective Languages
2016-09-05SSCLI RFP II Capstone Workshop ΓÇô Embedded Formal Verification Assistants in the .NET Framework
2016-09-05SSCLI RFP II Capstone Workshop ΓÇô Gardens Point Generics (GPG)
2016-09-05WACE 2005 - The Automated Lecture Capturing and Broadcasting System in MSRΓÇÖs 1159
2016-09-05Computer Aided Instruction in Graduate Compiler Design Based on the C# Compiler
2016-09-05SSCLI RFP II Capstone Workshop ΓÇô FreeSoDA
2016-09-05Predicting the Unpredictable
2016-09-05SSCLI RFP II Capstone Workshop ΓÇô Implementation of a Non-Strict Functional Language on Rotor
2016-09-05Performance and Feasibility of Capability-Based Security in the Rotor Platform
2016-09-05Moving VoIP beyond the phone
2016-09-05Examining representation, classification, and personalization using a unified framework
2016-09-05SSCLI RFP II Capstone Workshop ΓÇô RoSCtor: Software Construction Within Rotor
2016-09-05Extremal Set Theory, Boolean Functions, and Occam's Razor
2016-09-05A Voice-Enabled Procedure Navigator for the International Space Station
2016-09-05You can (almost) have it both! Low distortion texture mapping with Circle Patterns
2016-09-05Empirical Evaluation of Agile Software Development Processes: Industrial Case Studies
2016-09-05Designing Ad Auctions: An Algorithmic Perspective



Tags:
microsoft research