REVIEW 14 cited by
DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Probabilistic forecasting, i.e. estimating the probability distribution of a time series' future given its past, is a key enabler for optimizing business processes. In retail businesses, for example, forecasting demand is crucial for having the right inventory available at the right time at the right place. In this paper we propose DeepAR, a methodology for producing accurate probabilistic forecasts, based on training an auto regressive recurrent network model on a large number of related time series. We demonstrate how by applying deep learning techniques to forecasting, one can overcome many of the challenges faced by widely-used classical approaches to the problem. We show through extensive empirical evaluation on several real-world forecasting data sets accuracy improvements of around 15% compared to state-of-the-art methods.
Forward citations
Cited by 14 Pith papers
-
UC-Search: Risk-Aware Test-Time Search for Delayed Constrained Time-Series Control
UC-Search is a model-agnostic test-time wrapper that adds feasibility-automaton search and uncertainty-based risk adjustment to produce better delayed constrained control than CEM, MPPI, and risk-random baselines on p...
-
Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising
Decision-calibrated conformal uncertainty for pacing uses the support function of the signed policy sensitivity set to achieve smaller uncertainty radii on public datasets.
-
Expectations vs. Realities: The Cost of MSE-Optimal Forecasting Under Conditional Uncertainty
MSE-optimal multi-step forecasters cannot match the marginal distribution of realizations under nonzero conditional uncertainty, creating a quantifiable accuracy-realism Pareto frontier across benchmarks.
-
Bayesian evidence adaptive pursuit to identify neutron sources with scatter-based spectrometers
A new Bayesian search algorithm (BEAP) identifies single- and mixed-neutron-source compositions from recoil spectra with >4σ support in experiments and simulations.
-
Identifying Neutron Sources using Recoil and Time-of-Flight Spectroscopy
A Bayesian protocol identifies single- and two-source neutron configurations from spectra with greater than 4 sigma significance at event counts as low as 1000.
-
Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting
Logo-LLM improves time series forecasting by pulling local dynamics from shallow LLM layers and global trends from deeper layers, then aligning them via new Local-Mixer and Global-Mixer modules.
-
Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units
ARU embeds closed-form local linear models based on conditional Gaussian sufficient statistics into deep global forecasting networks for efficient streaming per-series adaptation.
-
DDOT: A Derivative-directed Dual-decoder Ordinary Differential Equation Transformer for Dynamic System Modeling
DDOT, a dual-decoder transformer with derivative prediction, reports improved symbolic ODE reconstruction on ODEBench and introduces a divergence-based metric, DIV-diff, for evaluating ODE hypotheses.
-
Towards Lightweight Time Series Forecasting: a Patch-wise Transformer with Weak Data Enriching
LiPFormer combines a simplified patch-wise Transformer with a CLIP-style contrastive module that exploits future covariates to forecast time series more accurately and efficiently.
-
Bayesian Active Learning By Distribution Disagreement
BALSA, a BALD variant that scores points by KL or Earth-Mover disagreement between dropout-sampled predictive distributions, outperforms standard uncertainty and clustering acquisition functions for regression with no...
-
Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine
Judiciously choosing just four datasets can make 46% of forecasting models appear best-in-class and 77% top-three, so dataset selection alone can distort reported performance.
-
MR-ImagenTime: Multi-Resolution Time Series Generation through Dual Image Representations
MR-CDM uses hierarchical multi-resolution decomposition and multi-scale conditional diffusion to generate forecasts that reduce MAE and RMSE by 6-10% versus baselines like CSDI and Informer on four datasets.
-
Intelligent Routing for Sparse Demand Forecasting: A Comparative Evaluation of Selection Strategies
A model-routing system that picks per-series forecasting models improves sparse demand forecast accuracy on Favorita by up to 11.8% over single-model benchmarks.
-
Fashion Retail: Forecasting Demand for New Items
Generalized ML models trained on past sales data forecast demand for new fashion items from their attributes, with experiments across neural architectures and loss functions showing robust performance.
Discussion (0). Continue with ORCID to comment.