A PDE Approach to the Prediction of a Binary Sequence with Advice from Two History-Dependent Experts

07/24/2020
by   Nadejda Drenska, et al.
0

The prediction of a binary sequence is a classic example of online machine learning. We like to call it the 'stock prediction problem,' viewing the sequence as the price history of a stock that goes up or down one unit at each time step. In this problem, an investor has access to the predictions of two or more 'experts,' and strives to minimize her final-time regret with respect to the best-performing expert. Probability plays no role; rather, the market is assumed to be adversarial. We consider the case when there are two history-dependent experts, whose predictions are determined by the d most recent stock moves. Focusing on an appropriate continuum limit and using methods from optimal control, graph theory, and partial differential equations, we discuss strategies for the investor and the adversarial market, and we determine associated upper and lower bounds for the investor's final-time regret. When d is less than 4 our upper and lower bounds coalesce, so the proposed strategies are asymptotically optimal. Compared to other recent applications of partial differential equations to prediction, ours has a new element: there are two timescales, since the recent history changes at every step whereas regret accumulates more slowly.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/31/2020

Online Prediction With History-Dependent Experts: The General Case

We study the problem of prediction of binary sequences with expert advic...
research
11/05/2019

New Potential-Based Bounds for Prediction with Expert Advice

This work addresses the classic machine learning problem of online predi...
research
08/31/2020

Asymptotically optimal strategies for online prediction with history-dependent experts

We establish sharp asymptotically optimal strategies for the problem of ...
research
04/25/2019

Prediction with Expert Advice: a PDE Perspective

This work addresses a classic problem of online prediction with expert a...
research
01/28/2020

Fast Rates for Online Prediction with Abstention

In the setting of sequential prediction of individual {0, 1}-sequences w...
research
07/23/2022

A New Approach to Drifting Games, Based on Asymptotically Optimal Potentials

We develop a new approach to drifting games, a class of two-person games...
research
12/05/2019

New Potential-Based Bounds for the Geometric-Stopping Version of Prediction with Expert Advice

This work addresses the classic machine learning problem of online predi...

Please sign up or login with your details

Forgot password? Click here to reset