Deep learning for time series forecasting has traditionally operated within a one-model-per-
dataset framework, limiting its potential to leverage the game-changing impact of large pre …

Deep learning has contributed remarkably to the advancement of time series analysis. Still,
deep models can encounter performance bottlenecks in real-world data-scarce scenarios …

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time
series models. Chronos tokenizes time series values using scaling and quantization into a …

Forecasting future events is important for policy and decision making. In this work, we study
whether language models (LMs) can forecast at the level of competitive human forecasters …

State of the art foundation models such as GPT-4 perform surprisingly well at in-context
learning (ICL), a variant of meta-learning concerning the learned ability to solve tasks during …

Tabular data, spreadsheets organized in rows and columns, are ubiquitous across scientific
fields, from biomedicine to particle physics to economics and climate science,. The …

Recent efforts have been dedicated to enhancing time series forecasting accuracy by
introducing advanced network architectures and self-supervised pretraining strategies …

Learning curve extrapolation aims to predict model performance in later epochs of training,
based on the performance in earlier epochs. In this work, we argue that, while the inherent …

Time series data are ubiquitous across various domains, making time series analysis
critically important. Traditional time series models are task-specific, featuring singular …

While tabular classification has traditionally relied on from-scratch training, a recent
breakthrough called prior-data fitted networks (PFNs) challenges this approach. Similar to …