Prediction with eventual almost sure guarantees

01/11/2020
by   Changlong Wu, et al.
0

We study the problem of predicting the properties of a probabilistic model and the next outcome of the model sequentially in the infinite horizon, so that the perdition will make finitely many errors with probability 1. We introduce a general framework that models such predication problems. We prove some general properties of the framework, and show some concrete examples with the application of such properties.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/12/2018

A Framework for Approval-based Budgeting Methods

We define and study a general framework for approval-based budgeting met...
research
02/18/2021

Error estimates for DeepOnets: A deep learning framework in infinite dimensions

DeepOnets have recently been proposed as a framework for learning nonlin...
research
05/31/2022

Concrete categories and higher-order recursion (With applications including probability, differentiability, and full abstraction)

We study concrete sheaf models for a call-by-value higher-order language...
research
07/24/2023

Domino Snake Problems on Groups

In this article we study domino snake problems on finitely generated gro...
research
10/27/2020

γ-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction

We introduce the γ-model, a predictive model of environment dynamics wit...
research
10/14/2017

Arbitrage-Free Regularization

We introduce a path-dependent geometric framework which generalizes the ...
research
08/21/2020

Tuple-Independent Representations of Infinite Probabilistic Databases

Probabilistic databases (PDBs) are probability spaces over database inst...

Please sign up or login with your details

Forgot password? Click here to reset