Abstract:Time series analysis by state-space models is widely used in forecasting and extracting unobservable components like level, slope, and seasonality, along with explanatory variables. However, their reliance on traditional Kalman filtering frequently hampers their effectiveness, primarily due to Gaussian assumptions and the absence of efficient subset selection methods to accommodate the multitude of potential explanatory variables in today's big-data applications. Our research introduces the State Space Learning (SSL), a novel framework and paradigm that leverages the capabilities of statistical learning to construct a comprehensive framework for time series modeling and forecasting. By utilizing a regularized high-dimensional regression framework, our approach jointly extracts typical time series unobservable components, detects and addresses outliers, and selects the influence of exogenous variables within a high-dimensional space in polynomial time and global optimality guarantees. Through a controlled numerical experiment, we demonstrate the superiority of our approach in terms of subset selection of explanatory variables accuracy compared to relevant benchmarks. We also present an intuitive forecasting scheme and showcase superior performances relative to traditional time series models using a dataset of 48,000 monthly time series from the M4 competition. We extend the applicability of our approach to reformulate any linear state space formulation featuring time-varying coefficients into high-dimensional regularized regressions, expanding the impact of our research to other engineering applications beyond time series analysis. Finally, our proposed methodology is implemented within the Julia open-source package, ``StateSpaceLearning.jl".
Abstract:Sequential Decision Making under Uncertainty (SDMU) is ubiquitous in many domains such as energy, finance, and supply chains. Some SDMU applications are naturally modeled as Multistage Stochastic Optimization Problems (MSPs), but the resulting optimizations are notoriously challenging from a computational standpoint. Under assumptions of convexity and stage-wise independence of the uncertainty, the resulting optimization can be solved efficiently using Stochastic Dual Dynamic Programming (SDDP). Two-stage Linear Decision Rules (TS-LDRs) have been proposed to solve MSPs without the stage-wise independence assumption. TS-LDRs are computationally tractable, but using a policy that is a linear function of past observations is typically not suitable for non-convex environments arising, for example, in energy systems. This paper introduces a novel approach, Two-Stage General Decision Rules (TS-GDR), to generalize the policy space beyond linear functions, making them suitable for non-convex environments. TS-GDR is a self-supervised learning algorithm that trains the nonlinear decision rules using stochastic gradient descent (SGD); its forward passes solve the policy implementation optimization problems, and the backward passes leverage duality theory to obtain closed-form gradients. The effectiveness of TS-GDR is demonstrated through an instantiation using Deep Recurrent Neural Networks named Two-Stage Deep Decision Rules (TS-DDR). The method inherits the flexibility and computational performance of Deep Learning methodologies to solve SDMU problems generally tackled through large-scale optimization techniques. Applied to the Long-Term Hydrothermal Dispatch (LTHD) problem using actual power system data from Bolivia, the TS-DDR not only enhances solution quality but also significantly reduces computation times by several orders of magnitude.
Abstract:The solution of multistage stochastic linear problems (MSLP) represents a challenge for many applications. Long-term hydrothermal dispatch planning (LHDP) materializes this challenge in a real-world problem that affects electricity markets, economies, and natural resources worldwide. No closed-form solutions are available for MSLP and the definition of non-anticipative policies with high-quality out-of-sample performance is crucial. Linear decision rules (LDR) provide an interesting simulation-based framework for finding high-quality policies to MSLP through two-stage stochastic models. In practical applications, however, the number of parameters to be estimated when using an LDR may be close or higher than the number of scenarios, thereby generating an in-sample overfit and poor performances in out-of-sample simulations. In this paper, we propose a novel regularization scheme for LDR based on the AdaLASSO (adaptive least absolute shrinkage and selection operator). The goal is to use the parsimony principle as largely studied in high-dimensional linear regression models to obtain better out-of-sample performance for an LDR applied to MSLP. Computational experiments show that the overfit threat is non-negligible when using the classical non-regularized LDR to solve MSLP. For the LHDP problem, our analysis highlights the following benefits of the proposed framework in comparison to the non-regularized benchmark: 1) significant reductions in the number of non-zero coefficients (model parsimony), 2) substantial cost reductions in out-of-sample evaluations, and 3) improved spot-price profiles.