GPs are highly expressive models that work well in the low data regime due to their Bayesian nature. However, applying GPs to PFL raises multiple challenges. Mainly, GPs performance depends heavily on access to a good kernel function, and learning a kernel requires a large training set.

Our model assumes a box prior,i.e., that the image captures either aninner viewor anouter viewof a box in 3D. It uses neural networks to infer visual cues such as vanishing points or wireframe lines to guide a search-based algorithm to find the program that best explains the image.

Furthermore, given random samples of pairwise comparisons, we show that a simple,"plug-in" estimator achieves(near-)optimal minimax samplecomplexity.

Furthermore, given random samples of pairwise comparisons, we show that a simple,"plug-in" estimator achieves(near-)optimal minimax samplecomplexity.

While deep learning (DL) models have demonstrated impressive performance over a range of complicated tasksanddatamodalities, ithasremained difficulttoquantify theuncertainty fortheir predictions.

Under 2.1, 2.3, 5.1, 5.2 and 5.3, let x , ( 0) X , ( 0) xinit 2 U forall , >0 for SGD+WD(2) and SDE(3).

It clearly shows thatBEstudents distilled withODSare better calibrated than the baselines. The difference is that the adversarial perturbation is meant to worsen the predictive performance by design because it takes astep toward the directions increasing the classification loss. Weempirically found that the perturbations just increasing diversity without maintaining prediction accuracy can actually harm the performance of student models (this is also related to the performance gain of ConfODS). Table 4: Knowledge distillation fromDE-3 into MIMO-3: ACC, standard metricsand calibrated metrics.