2 citations · 4 across the 17 of their papers we have counts for
4 papers · 1 filter
Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees
Sangwoo Park, Matteo Zecchin, Osvaldo Simeone
Selecting artificial intelligence (AI) models, such as large language models (LLMs), from multiple candidates requires accurate performance estimation. This is ideally achieved thr…
Online Conformal Probabilistic Numerics via Adaptive Edge-Cloud Offloading
Qiushuo Hou, Sangwoo Park, Matteo Zecchin +3
Consider an edge computing setting in which a user submits queries for the solution of a linear system to an edge processor, which is subject to time-varying computing availability…
Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection
Matteo Zecchin, Sangwoo Park, Osvaldo Simeone
We introduce adaptive learn-then-test (aLTT), an efficient hyperparameter selection procedure that provides finite-sample statistical guarantees on the population risk of AI models…
Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal Prediction
Sangwoo Park, Kfir M. Cohen, Osvaldo Simeone
Conventional frequentist learning is known to yield poorly calibrated models that fail to reliably quantify the uncertainty of their decisions. Bayesian learning can improve calibr…