5 papers
Meta-Learning at Scale for Large Language Models via Low-Rank Amortized Bayesian Meta-Learning
Liyi Zhang, Jake Snell, Thomas L. Griffiths
Fine-tuning large language models (LLMs) with low-rank adaptation (LoRA) is a cost-effective way to incorporate information from a specific dataset. However, when a problem require…
Conformal Prediction as Bayesian Quadrature
Jake C. Snell, Thomas L. Griffiths
As machine learning-based prediction systems are increasingly used in high-stakes situations, it is important to understand how such predictive models will perform upon deployment.…
Learning Human-Aligned Representations with Contrastive Learning and Generative Similarity
Raja Marjieh, Sreejan Kumar, Declan Campbell +4
Humans rely on effective representations to learn from few examples and abstract useful information from sensory data. Inducing such representations in machine learning models has…
A Metalearned Neural Circuit for Nonparametric Bayesian Inference
Jake C. Snell, Gianluca Bencomo, Thomas L. Griffiths
Most applications of machine learning to classification assume a closed set of balanced classes. This is at odds with the real world, where class occurrence statistics often follow…
Implicit Maximum a Posteriori Filtering via Adaptive Optimization
Gianluca M. Bencomo, Jake C. Snell, Thomas L. Griffiths
Bayesian filtering approximates the true underlying behavior of a time-varying system by inverting an explicit generative model to convert noisy measurements into state estimates.…