AltTS: A Dual-Path Framework with Alternating Optimization for Multivariate Time Series Forecasting
This work addresses the challenge of robust long-horizon forecasting in multivariate time series, which is critical for applications like finance and climate modeling, by introducing a novel optimization strategy rather than incremental architectural changes.
The paper tackles the problem of multivariate time series forecasting by addressing the optimization conflict between autoregressive dynamics and cross-dimension interactions, proposing a dual-path framework with alternating optimization that improves long-horizon accuracy, achieving consistent outperformance over prior methods on multiple benchmarks.
Multivariate time series forecasting involves two qualitatively distinct factors: (i) stable within-series autoregressive (AR) dynamics, and (ii) intermittent cross-dimension interactions that can become spurious over long horizons. We argue that fitting a single model to capture both effects creates an optimization conflict: the high-variance updates needed for cross-dimension modeling can corrupt the gradients that support autoregression, resulting in brittle training and degraded long-horizon accuracy. To address this, we propose ALTTS, a dual-path framework that explicitly decouples autoregression and cross-relation (CR) modeling. In ALTTS, the AR path is instantiated with a linear predictor, while the CR path uses a Transformer equipped with Cross-Relation Self-Attention (CRSA); the two branches are coordinated via alternating optimization to isolate gradient noise and reduce cross-block interference. Extensive experiments on multiple benchmarks show that ALTTS consistently outperforms prior methods, with the most pronounced improvements on long-horizon forecasting. Overall, our results suggest that carefully designed optimization strategies, rather than ever more complex architectures, can be a key driver of progress in multivariate time series forecasting.