Ching-An Cheng

Intra Order-preserving Functions for Calibration of Multi-Class Neural\n Networks

2020 · arXiv (Cornell University)

Predicting calibrated confidence scores for multi-class deep networks is\nimportant for avoiding rare but costly mistakes. A common approach is to learn\na post-hoc calibration function that transforms the output of the original\nnetwork into calibrated confidence scores …

How to Solve Contextual Goal-Oriented Problems with Offline Datasets?

2024 · arXiv (Cornell University)

We present a novel method, Contextual goal-Oriented Data Augmentation (CODA), which uses commonly available unlabeled trajectories and context-goal pairs to solve Contextual Goal-Oriented (CGO) problems. By carefully constructing an action-augmented MDP that is equivalent to …