4 papers
Interventional Flow Matching: Prospective Dose-Response Forecasting with Velocity-Field Jacobian Regularization
Amirreza Dolatpour Fathkouhi, Justin Lee, Heman Shakeri
Predicting a patient's physiological trajectory under a planned treatment sequence is a prospective interventional problem, not standard time-series extrapolation. We study this pr…
The Stationarity Bias: Stratified Stress-Testing for Time-Series Imputation in Regulated Dynamical Systems
Amirreza Dolatpour Fathkouhi, Alireza Namazi, Heman Shakeri
Time-series imputation benchmarks employ uniform random masking and shape-agnostic metrics (MSE, RMSE), implicitly weighting evaluation by regime prevalence. In systems with a domi…
Mitigating Exposure Bias in Risk-Aware Time Series Forecasting with Soft Tokens
Alireza Namazi, Amirreza Dolatpour Fathkouhi, Heman Shakeri
Autoregressive forecasting is central to predictive control in diabetes and hemodynamic management, where different operating zones carry different clinical risks. Standard models…
AstroMAE: Redshift Prediction Using a Masked Autoencoder with a Novel Fine-Tuning Architecture
Amirreza Dolatpour Fathkouhi, Geoffrey Charles Fox
Redshift prediction is a fundamental task in astronomy, essential for understanding the expansion of the universe and determining the distances of astronomical objects. Accurate re…