Time-Varying Optimization for Streaming Data Via Temporal Weighting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abrar, Muhammad Faraz Ul, Michelusi, Nicolò, Larsson, Erik G.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909847145938944
author Abrar, Muhammad Faraz Ul
Michelusi, Nicolò
Larsson, Erik G.
author_facet Abrar, Muhammad Faraz Ul
Michelusi, Nicolò
Larsson, Erik G.
contents Classical optimization theory deals with fixed, time-invariant objective functions. However, time-varying optimization has emerged as an important subject for decision-making in dynamic environments. In this work, we study the problem of learning from streaming data through a time-varying optimization lens. Unlike prior works that focus on generic formulations, we introduce a structured, \emph{weight-based} formulation that explicitly captures the streaming-data origin of the time-varying objective, where at each time step, an agent aims to minimize a weighted average loss over all the past data samples. We focus on two specific weighting strategies: (1) uniform weights, which treat all samples equally, and (2) discounted weights, which geometrically decay the influence of older data. For both schemes, we derive tight bounds on the ``tracking error'' (TE), defined as the deviation between the model parameter and the time-varying optimum at a given time step, under gradient descent (GD) updates. We show that under uniform weighting, the TE vanishes asymptotically with a $\mathcal{O}(1/t)$ decay rate, whereas discounted weighting incurs a nonzero error floor controlled by the discount factor and the number of gradient updates performed at each time step. Our theoretical findings are validated through numerical simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13052
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Time-Varying Optimization for Streaming Data Via Temporal Weighting
Abrar, Muhammad Faraz Ul
Michelusi, Nicolò
Larsson, Erik G.
Machine Learning
Artificial Intelligence
Systems and Control
Signal Processing
Optimization and Control
Classical optimization theory deals with fixed, time-invariant objective functions. However, time-varying optimization has emerged as an important subject for decision-making in dynamic environments. In this work, we study the problem of learning from streaming data through a time-varying optimization lens. Unlike prior works that focus on generic formulations, we introduce a structured, \emph{weight-based} formulation that explicitly captures the streaming-data origin of the time-varying objective, where at each time step, an agent aims to minimize a weighted average loss over all the past data samples. We focus on two specific weighting strategies: (1) uniform weights, which treat all samples equally, and (2) discounted weights, which geometrically decay the influence of older data. For both schemes, we derive tight bounds on the ``tracking error'' (TE), defined as the deviation between the model parameter and the time-varying optimum at a given time step, under gradient descent (GD) updates. We show that under uniform weighting, the TE vanishes asymptotically with a $\mathcal{O}(1/t)$ decay rate, whereas discounted weighting incurs a nonzero error floor controlled by the discount factor and the number of gradient updates performed at each time step. Our theoretical findings are validated through numerical simulations.
title Time-Varying Optimization for Streaming Data Via Temporal Weighting
topic Machine Learning
Artificial Intelligence
Systems and Control
Signal Processing
Optimization and Control
url https://arxiv.org/abs/2510.13052