Scalable AI Uncertainty Quantification via Generalized Laplace Active Subspaces

Key points

• Reliable uncertainty quantification (UQ) is essential for deploying neural networks in scientific and high-stakes applications, but full Bayesian inference over the network parameters is computationally infeasible.1
• Starting from a generalized Bayesian posterior defined through an empirical loss, we construct a local Gaussian approximation around a pretrained set of weights in this active curvature subspace.1
• The generalized Bayesian formulation allows us to compare two posterior scalings: the standard Bayesian scaling associated with the summed negative log likelihood, and a mean-loss scaling in which the empirical loss is normalized by the number of data.1
• These results indicate that generalized Laplace active subspaces provide a practical and scalable route to calibrated uncertainty quantification in neural networks.1

Sources (1)

• [1]Scalable AI Uncertainty Quantification via Generalized Laplace Active Subspaces
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 11:31 AM

  We propose a low-rank generalized Laplace approximation for neural-network UQ based on a small number of data-informed curvature directions.

  Reliable uncertainty quantification (UQ) is essential for deploying neural networks in scientific and high-stakes applications, but full Bayesian inference over the network parameters is computationally infeasible.

Extractive summary: sentences quoted from the sources.