14 papers
Bootstrap-Conditioned Action Selection with Tabular Foundation Models
Devansh Gupta, Shiv Tavker, Dmitry Efimov +3
Contextual bandits offer a natural framework for sample-efficient personalization, but practical deployment remains difficult under sparse, biased interaction data, unreliable unce…
Post-Training in Time Series Foundation Models: A Unifying Framework
Shifeng Xie, Ambroise Odonnat, Zehao Xiao +7
Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deploymen…
Forking-Sequences: Statistically and Computationally Efficient Multi-Horizon Forecasting with Reduced Volatility
Willa Potosnak, Malcolm Wolff, Mengfei Cao +6
While accuracy is a critical requirement for time series forecasting, an equally important desideratum is reasonable forecast volatility across forecast creation dates (FCDs). Even…
Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables
Andres Potapczynski, Ravi Kiran Selvam, Tatiana Konstantinova +9
In many time series forecasting settings, the target time series is accompanied by exogenous covariates, such as promotions and prices in retail demand; temperature in energy load;…
Online Posterior Sampling with a Diffusion Prior
Branislav Kveton, Boris Oreshkin, Youngsuk Park +2
Posterior sampling in contextual bandits with a Gaussian prior can be implemented exactly or approximately using the Laplace approximation. The Gaussian prior is computationally ef…
Zero-shot Forecasting by Simulation Alone
Boris N. Oreshkin, Mayank Jauhari, Ravi Kiran Selvam +10
Zero-shot time-series forecasting holds great promise, but is still in its infancy, hindered by limited and biased data corpora, leakage-prone evaluation, and privacy and licensing…