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

5 Mar 2020  ·  Cuong Nguyen, Thanh-Toan Do, Gustavo Carneiro ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) SImPa Accuracy 52.11 # 76
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) SImPa Accuracy 63.87 # 76
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) SImPa Accuracy 70.82 # 25
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) SImPa Accuracy 81.84 # 32

Methods


No methods listed for this paper. Add relevant methods here