activity
20242026
collaborators

6 papers

cs.LG2026

Elicitation without Backpropagation: Steering Model Behavior by Optimizing the Latent Posterior

Garrett Baker, Vinayak Pathak, Daniel Murfet +1

In the \emph{latent posterior model} of transformer behavior, the next-token distribution arises from a posterior over latent predictive models conditioned on the context, mixed to…

cs.LG2026

What does a Bayes-filtered transformer believe? A predictive Monte Carlo approach

Afiq Abdillah Effiezal Aswadi, Haotong Ma, Susan Wei

A Bayes-filtered transformer (BFT) is a transformer trained on sequences that are generated in two steps: first a latent task is drawn from a prior, then observations are drawn con…

stat.ME2026

TabMGP: Martingale Posterior with TabPFN

Kenyon Ng, Edwin Fong, David T. Frazier +2

Bayesian inference provides principled uncertainty quantification but is often limited by the challenges of prior and likelihood elicitation. The martingale posterior (MGP) (Fong e…

stat.ML2026

Uncertainty Decomposition for Bayes-Filtered Transformers via Bayesian Predictive Inference

Sandra Fortini, Kenyon Ng, Sonia Petrone +2

Bayes-filtered transformers are transformers meta-learned on sequences from a prior predictive distribution to approximate the corresponding posterior predictive distribution. They…

stat.ML2025

Temperature Optimization for Bayesian Deep Learning

Kenyon Ng, Chris van der Heide, Liam Hodgkinson +1

The Cold Posterior Effect (CPE) is a phenomenon in Bayesian Deep Learning (BDL), where tempering the posterior to a cold temperature often improves the predictive performance of th…

stat.ML2024

Pathwise Gradient Variance Reduction with Control Variates in Variational Inference

Kenyon Ng, Susan Wei

Variational inference in Bayesian deep learning often involves computing the gradient of an expectation that lacks a closed-form solution. In these cases, pathwise and score-functi…