Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting

• URL: http://arxiv.org/abs/2410.03229v1
• Date: Fri, 4 Oct 2024 08:34:14 GMT
• Title: Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting
• Authors: Soon Hoe Lim, Yijin Wang, Annan Yu, Emma Hart, Michael W. Mahoney, Xiaoye S. Li, N. Benjamin Erichson,
• Abstract summary: Flow matching has recently emerged as a powerful paradigm generative modeling. We show that forecasting-temporal data with flow matching is highly sensitive to selection of the probability path model. Motivated by this insight, we propose a novel probability path model to improve forecasting performance.
• Score: 44.24834367720476
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flow matching has recently emerged as a powerful paradigm for generative modeling and has been extended to probabilistic time series forecasting in latent spaces. However, the impact of the specific choice of probability path model on forecasting performance remains under-explored. In this work, we demonstrate that forecasting spatio-temporal data with flow matching is highly sensitive to the selection of the probability path model. Motivated by this insight, we propose a novel probability path model designed to improve forecasting performance. Our empirical results across various dynamical system benchmarks show that our model achieves faster convergence during training and improved predictive performance compared to existing probability path models. Importantly, our approach is efficient during inference, requiring only a few sampling steps. This makes our proposed model practical for real-world applications and opens new avenues for probabilistic forecasting.

Related papers

• Motion Forecasting via Model-Based Risk Minimization [8.766024024417316]
  We propose a novel sampling method applicable to trajectory prediction based on the predictions of multiple models. We first show that conventional sampling based on predicted probabilities can degrade performance due to missing alignment between models. By using state-of-the-art models as base learners, our approach constructs diverse and effective ensembles for optimal trajectory sampling.
  arXiv  Detail & Related papers  (2024-09-16T09:03:28Z)
• Predictive Churn with the Set of Good Models [64.05949860750235]
  We study the effect of conflicting predictions over the set of near-optimal machine learning models. We present theoretical results on the expected churn between models within the Rashomon set. We show how our approach can be used to better anticipate, reduce, and avoid churn in consumer-facing applications.
  arXiv  Detail & Related papers  (2024-02-12T16:15:25Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2023-10-17T20:30:16Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2022-06-16T06:13:53Z)
• Planning with Diffusion for Flexible Behavior Synthesis [125.24438991142573]
  We consider what it would look like to fold as much of the trajectory optimization pipeline as possible into the modeling problem. The core of our technical approach lies in a diffusion probabilistic model that plans by iteratively denoising trajectories.
  arXiv  Detail & Related papers  (2022-05-20T07:02:03Z)
• Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization [5.5643498845134545]
  We use generative neural networks to parametrize distributions on high-dimensional spaces by transforming draws from a latent variable. We train generative networks to minimize a predictive-sequential (or prequential) scoring rule on a recorded temporal sequence of the phenomenon of interest. Our method outperforms state-of-the-art adversarial approaches, especially in probabilistic calibration.
  arXiv  Detail & Related papers  (2021-12-15T15:51:12Z)
• Autoregressive Quantile Flows for Predictive Uncertainty Estimation [7.184701179854522]
  We propose Autoregressive Quantile Flows, a flexible class of probabilistic models over high-dimensional variables. These models are instances of autoregressive flows trained using a novel objective based on proper scoring rules.
  arXiv  Detail & Related papers  (2021-12-09T01:11:26Z)
• Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting [98.57851612518758]
  Probabilistic time series forecasting involves estimating the distribution of future based on its history. We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks. We show in experiments that our model produces accurate and sharp probabilistic forecasts.
  arXiv  Detail & Related papers  (2021-01-31T06:49:33Z)
• A Worrying Analysis of Probabilistic Time-series Models for Sales Forecasting [10.690379201437015]
  Probabilistic time-series models become popular in the forecasting field as they help to make optimal decisions under uncertainty. We analyze the performance of three prominent probabilistic time-series models for sales forecasting.
  arXiv  Detail & Related papers  (2020-11-21T03:31:23Z)
• Adversarial Attacks on Probabilistic Autoregressive Forecasting Models [7.305979446312823]
  We develop an effective generation of adversarial attacks on neural models that output a sequence of probability distributions rather than a sequence of single values. We demonstrate that our approach can successfully generate attacks with small input perturbations in two challenging tasks.
  arXiv  Detail & Related papers  (2020-03-08T13:08:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.