1 citations · 1 across the 1 of their papers we have counts for
8 papers
fev-bench: A Realistic Benchmark for Time Series Forecasting
Oleksandr Shchur, Abdul Fatir Ansari, Caner Turkmen +5
Benchmark quality is critical for meaningful evaluation and sustained progress in time series forecasting, particularly with the rise of pretrained models. Existing benchmarks ofte…
Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting
Mert Kayaalp, Caner Turkmen, Oleksandr Shchur +4
Is bigger always better for time series foundation models? With the question in mind, we explore an alternative to training a single, large monolithic model: building a portfolio o…
Multi-layer Stack Ensembles for Time Series Forecasting
Nathanael Bosch, Oleksandr Shchur, Nick Erickson +2
Ensembling is a powerful technique for improving the accuracy of machine learning models, with methods like stacking achieving strong results in tabular tasks. In time series forec…
Understanding the Implicit Biases of Design Choices for Time Series Foundation Models
Annan Yu, Danielle C. Maddix, Boran Han +7
Time series foundation models (TSFMs) are a class of potentially powerful, general-purpose tools for time series forecasting and related temporal tasks, but their behavior is stron…
Chronos-2: From Univariate to Universal Forecasting
Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken +20
Pretrained time series models have enabled inference-only forecasting systems that produce accurate predictions without task-specific training. However, existing approaches largely…
Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
Annan Yu, Danielle C. Maddix, Boran Han +7
Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly to models trained to other modalities. In this pap…