Nathaniel Diamant — accepted AI-conference papers

2026

Calibrating Generative Models to Distributional Constraints

Henry Smith, Nathaniel Diamant, Brian Trippe

ICML 2026poster

Generative models frequently suffer miscalibration, wherein statistics of the sampling distribution such as class probabilities deviate from desired values. We frame calibration as a constrained optimization problem and seek the closest model in Kullback-Leibler divergence satisfying calibration con…

Cited by 0 Source ↗Scholar ↗

2024

Conformalized Deep Splines for Optimal and Efficient Prediction Sets

Nathaniel Diamant, Ehsan Hajiramezanali, Tommaso Biancalani, Gabriele Scalia

AISTATS 2024poster

Uncertainty estimation is critical in high-stakes machine learning applications. One effective way to estimate uncertainty is conformal prediction, which can provide predictive inference with statistical coverage guarantees. We present a new conformal regression method, Spline Prediction Intervals v…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗