61 citations · 63 across the 11 of their papers we have counts for
11 papers
Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models
Xiyuan Zhang, Danielle C. Maddix, Junming Yin +11
Since the seminal work of TabPFN, research on tabular foundation models (TFMs) based on in-context learning (ICL) has challenged long-standing paradigms in machine learning. Withou…
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…
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…
When Does Multimodality Lead to Better Time Series Forecasting?
Xiyuan Zhang, Boran Han, Haoyang Fang +11
Recently, there has been growing interest in incorporating textual information into foundation models for time series forecasting. However, it remains unclear whether and under wha…
End-to-End Probabilistic Framework for Learning with Hard Constraints
Utkarsh Utkarsh, Danielle C. Maddix, Ruijun Ma +2
We present ProbHardE2E, a probabilistic forecasting framework that incorporates hard operational/physical constraints, and provides uncertainty quantification. Our methodology uses…
Using Pre-trained LLMs for Multivariate Time Series Forecasting
Malcolm L. Wolff, Shenghao Yang, Kari Torkkola +1
Pre-trained Large Language Models (LLMs) encapsulate large amounts of knowledge and take enormous amounts of compute to train. We make use of this resource, together with the obser…
Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
Luca Masserano, Abdul Fatir Ansari, Boran Han +8
How to best develop foundational models for time series forecasting remains an important open question. Tokenization is a crucial consideration in this effort: what is an effective…
Gradient-Free Generation for Hard-Constrained Systems
Chaoran Cheng, Boran Han, Danielle C. Maddix +4
Generative models that satisfy hard constraints are critical in many scientific and engineering applications, where physical laws or system requirements must be strictly respected.…
Comparing and Contrasting DLWP Backbones on Navier-Stokes and Atmospheric Dynamics
Matthias Karlbauer, Danielle C. Maddix, Abdul Fatir Ansari +5
A large number of Deep Learning Weather Prediction (DLWP) architectures -- based on various backbones, including U-Net, Transformer, Graph Neural Network, and Fourier Neural Operat…
Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs
S. Chandra Mouli, Danielle C. Maddix, Shima Alizadeh +4
Existing work in scientific machine learning (SciML) has shown that data-driven learning of solution operators can provide a fast approximate alternative to classical numerical par…
Chronos: Learning the Language of Time Series
Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen +15
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 f…