Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization

Pacchiardi, Lorenzo1; Adewoyin, Rilwan A.2,4; Dueben, Peter3; Dutta, Ritabrata2

2024

JOURNAL OF MACHINE LEARNING RESEARCH   影响因子和分区

1532-4435

Probabilistic forecasting relies on past observations to provide a probability distribution for a future outcome, which is often evaluated against the realization using a scoring rule. Here, we perform probabilistic forecasting with generative neural networks, which parametrize distributions on high -dimensional spaces by transforming draws from a latent variable. Generative networks are typically trained in an adversarial framework. In contrast, we propose to train generative networks to minimize a predictive -sequential (or prequential) scoring rule on a recorded temporal sequence of the phenomenon of interest, which is appealing as it corresponds to the way forecasting systems are routinely evaluated. Adversarial -free minimization is possible for some scoring rules; hence, our framework avoids the cumbersome hyperparameter tuning and uncertainty underestimation due to unstable adversarial training, thus unlocking reliable use of generative networks in probabilistic forecasting. Further, we prove consistency of the minimizer of our objective with dependent data, while adversarial training assumes independence. We perform simulation studies on two chaotic dynamical models and a benchmark data set of global weather observations; for this last example, we define scoring rules for spatial data by drawing from the relevant literature. Our method outperforms state-of-the-art adversarial approaches, especially in probabilistic calibration, while requiring less hyperparameter tuning.

Generative Networks GAN Probabilistic Forecasting Scoring Rules Adversarial-free

SCI

英语

其他

EPSRC["EP/V025899/1","EP/T017112/1","EP/L016710/1"] ; MRC through the OxWaSP CDT programme[EP/L016710/1] ; NERC[NE/T00973X/1] ; ESiWACE Horizon 2020 project[823988] ; MAELSTROM EuroHPC Joint Undertaking project[955513]

Automation & Control Systems ; Computer Science

Automation & Control Systems ; Computer Science, Artificial Intelligence

WOS:001185341600001

MICROTOME PUBL

COMPUTER SCIENCE

Web of Science

1.Univ Oxford, Dept Stat, Oxford OX1 SLB, England
2.Univ Warwick, Dept Stat, Coventry CV4 7AL, W Midlands, England
3.European Ctr Medium Range Weather Forecasts, Earth Syst Modelling Sect, Reading RG2 9AX, Berks, England
4.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China

Pacchiardi, Lorenzo,Adewoyin, Rilwan A.,Dueben, Peter,et al. Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization[J]. JOURNAL OF MACHINE LEARNING RESEARCH,2024,25.

Pacchiardi, Lorenzo,Adewoyin, Rilwan A.,Dueben, Peter,&Dutta, Ritabrata.(2024).Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization.JOURNAL OF MACHINE LEARNING RESEARCH,25.

Pacchiardi, Lorenzo,et al."Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization".JOURNAL OF MACHINE LEARNING RESEARCH 25(2024).