ICML 2021 accepted papers on Time series
16 of the 1,184 papers accepted at ICML 2021 (1.4%) are on Time series, compared with 0.8% at ICML 2020. They fall into 3 topics.
See ICML 2021 in the interactive map
Submitting to ICML? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Causal and generative time series · 12 papers
- Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting (43 citations)
- Neural Rough Differential Equations for Long Time Series (33 citations)
- Explaining Time Series Predictions with Dynamic Masks (32 citations)
- End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series (29 citations)
- Conformal prediction interval for dynamic time-series (14 citations)
- Variance Reduced Training with Stratified Sampling for Forecasting Models (5 citations)
- Whittle Networks: A Deep Likelihood Model for Time Series (5 citations)
- Neural Pharmacodynamic State Space Modeling (4 citations)
- Policy Analysis using Synthetic Controls in Continuous-Time (4 citations)
- RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting (3 citations)
- Approximation Theory of Convolutional Architectures for Time Series Modelling (2 citations)
- STRODE: Stochastic Boundary Ordinary Differential Equation (1 citation)
