# PAC-Bayes meta-learning with implicit task-specific posteriors

arXiv: https://arxiv.org/abs/2003.02455 · HTML: https://mlsanity.com/paper/2003.02455/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms](https://mlsanity.com/paper/2402.04054/) (2024)
- [Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks](https://mlsanity.com/paper/2107.02378/) (2021)
- [Streaming PAC-Bayes Gaussian process regression with a performance guarantee for online decision making](https://mlsanity.com/paper/2210.08486/) (2022)
- [BATR-FST: Bi-Level Adaptive Token Refinement for Few-Shot Transformers](https://mlsanity.com/paper/2509.12768/) (2025)

## Abstract (arXiv)

We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single task setting to the meta-learning multiple task setting to upper-bound the error evaluated on any, even unseen, tasks and samples. We also propose a generative-based approach to estimate the posterior of task-specific model parameters more expressively compared to the usual assumption based on a multivariate normal distribution with a diagonal covariance matrix. We show that the models trained with our proposed meta-learning algorithm are well calibrated and accurate, with state-of-the-art calibration and classification results on few-shot classification (mini-ImageNet and tiered-ImageNet) and regression (multi-modal task-distribution regression) benchmarks.