Time-Varying Optimization for Streaming Data Via Temporal Weighting
By: Muhammad Faraz Ul Abrar, Nicolò Michelusi, Erik G. Larsson
Potential Business Impact:
Learns from changing information to make better choices.
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.
Similar Papers
Temporal Variabilities Limit Convergence Rates in Gradient-Based Online Optimization
Optimization and Control
Makes computers learn faster when things change.
The Interplay of Statistics and Noisy Optimization: Learning Linear Predictors with Random Data Weights
Machine Learning (Stat)
Makes computer learning faster and more accurate.
Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
Machine Learning (CS)
Teaches AI to balance many goals at once.