Nathan Hoyen Ng — accepted AI-conference papers

2024

Measuring Stochastic Data Complexity with Boltzmann Influence Functions

Nathan Hoyen Ng, Roger Baker Grosse, Marzyeh Ghassemi

ICML 2024poster

Estimating the uncertainty of a model’s prediction on a test point is a crucial part of ensuring reliability and calibration under distribution shifts.A minimum description length approach to this problem uses the predictive normalized maximum likelihood (pNML) distribution, which considers every po…

Cited by 1 Source ↗PDF ↗Scholar ↗

2022

If Influence Functions are the Answer, Then What is the Question?

Juhan Bae, Nathan Hoyen Ng, Alston Lo, Marzyeh Ghassemi, Roger Baker Grosse

NeurIPS 2022accept

Influence functions efficiently estimate the effect of removing a single training data point on a model's learned parameters. While influence estimates align well with leave-one-out retraining for linear models, recent works have shown this alignment is often poor in neural networks. In this work, w…

Cited by 114 Source ↗PDF ↗code ↗Scholar ↗