Feature-aligned N-BEATS with Sinkhorn divergence
We propose Feature-aligned N-BEATS as a domain-generalized time series forecasting model. It is a nontrivial extension of N-BEATS with doubly residual stacking principle (Oreshkin et al. [45]) into a representation learning framework. In particular, it revolves around marginal feature probability measures induced by the intricate composition of residual and feature extracting operators of N-BEATS in each stack and aligns them stack-wise via an approximate of an optimal transport distance referred to as the Sinkhorn divergence. The training loss consists of an empirical risk minimization from multiple source domains, i.e., forecasting loss, and an alignment loss calculated with the Sinkhorn divergence, which allows the model to learn invariant features stack-wise across multiple source data sequences while retaining N-BEATS's interpretable design and forecasting power. Comprehensive experimental evaluations with ablation studies are provided and the corresponding results demonstrate the proposed model's forecasting and generalization capabilities.
Code (1)
Tasks
Domain GeneralizationRepresentation LearningTime SeriesTime Series ForecastingUnivariate Time Series ForecastingSimilar Papers 제목 키워드 기반
Hilbert Sinkhorn Divergence for Optimal Transport
Sinkhorn divergence has become a very popular metric to compare probability distributions in optimal transport. However, most works resort to Sinkhorn divergence in Euclidean space, which greatly blocks their applica…
image-classificationImage ClassificationTopological Data AnalysisDistributional Reinforcement Learning with Regularized Wasserstein Loss
The empirical success of distributional reinforcement learning (RL) highly relies on the choice of distribution divergence equipped with an appropriate distribution representation. In this paper, we propose \textit{Sinkh…
Atari GamesDistributional Reinforcement Learningreinforcement-learningReinforcement Learning+1Convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings
This work studies the convergence and finite sample approximations of entropic regularized Wasserstein distances in the Hilbert space setting. Our first main result is that for Gaussian measures on an infinite-dimensiona…
Sinkhorn-Drifting Generative Models
We establish a theoretical link between the recently proposed "drifting" generative dynamics and gradient flows induced by the Sinkhorn divergence. In a particle discretization, the drift field admits a cross-minus-self …
Optimal transport with $f$-divergence regularization and generalized Sinkhorn algorithm
Entropic regularization provides a generalization of the original optimal transport problem. It introduces a penalty term defined by the Kullback-Leibler divergence, making the problem more tractable via the celebrated S…