Fourier minimization and imputation of time series

TL;DR

This paper adapts classical L1 minimization techniques for signal recovery to the problem of imputing missing values in time series data, supported by theoretical justifications and preliminary numerical tests.

Contribution

It introduces a novel application of L1 minimization methods for time series imputation, grounded in advanced mathematical theory.

Findings

Theoretical support from Bourgain, Talagrand, and others for the method.

Preliminary numerical tests demonstrate potential effectiveness.

Framework sets the stage for more extensive future evaluations.

Abstract

One of the most common procedures in modern data analytics is filling in missing values in times series. For a variety of reasons, the data provided by clients to obtain a forecast, or other forms of data analysis, may have missing values, and those values need to be filled in before the data set can be properly analyzed. Many freely available forecasting software packages, such as the sktime library, have built-in mechanisms for filling in missing values. The purpose of this paper is to adapt the classical $L^1$ minimization method for signal recovery to the filling of missing values in times. The theoretical justifications of these methods leverage results by Bourgain (\cite{Bourgain89}), Talagrand (\cite{Talagrand98}), the second and the third listed authors (\cite{IM24}), and the result by the second listed author, Kashin, Limonova and the third listed author (\cite{IKLM24}). Brief numerical tests for these algorithms are given but more extensive will be discussed in a companion paper.