Packed Ensembles for efficient uncertainty estimation

Authors: Olivier Laurent, Adrien Lafage, Enzo Tartaglione, Geoffrey Daniel, Jean-marc Martinez, Andrei Bursuc, Gianni Franchi

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our extensive research indicates that PE accurately preserves the properties of DE, such as diversity, and performs equally well in terms of accuracy, calibration, out-of-distribution detection, and robustness to distribution shift. We make our code available at github.com/ENSTAU2IS/torch-uncertainty. and 4 EXPERIMENTS To validate the performance of our method, we conduct experiments on classification tasks and measure the influence of the parameters α and γ.
Researcher Affiliation Collaboration Olivier Laurent,1,2,* Adrien Lafage,2,* Enzo Tartaglione,3 Geoffrey Daniel,1 Jean-Marc Martinez,1 Andrei Bursuc4 & Gianni Franchi2, Universit e Paris-Saclay, CEA, SGLS,1 U2IS, ENSTA Paris, Institut Polytechnique de Paris,2 LTCI, T el ecom Paris, Institut Polytechnique de Paris,3 valeo.ai4
Pseudocode No The paper describes mathematical formulations and implementation details (e.g., equations for convolutional layers, architectural diagrams in Figure 3) but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes We make our code available at github.com/ENSTAU2IS/torch-uncertainty. and To further promote accessibility, we have created an open-source pip-installable Py Torch package, torch-uncertainty, that includes Packed-Ensembles layers.
Open Datasets Yes First, we demonstrate the efficiency of Packed-Ensembles on CIFAR-10 and CIFAR100 (Krizhevsky, 2009), showing how the method adapts to tasks of different complexities. and Second, we report our results for Packed-Ensembles on Image Net (Deng et al., 2009), which we compare against all baselines.
Dataset Splits Yes First, we demonstrate the efficiency of Packed-Ensembles on CIFAR-10 and CIFAR100 (Krizhevsky, 2009)... and Second, we report our results for Packed-Ensembles on Image Net (Deng et al., 2009)... and We use accuracy as the validation criterion (i.e., the final trained model is the one with the highest accuracy).
Hardware Specification Yes Most training instances are completed on a single Nvidia RTX 3090 except for Image Net, for which we use 2 to 8 Nvidia A100-80GB.
Software Dependencies Yes Table 8: Comparison of training and inference times of different ensemble techniques using torch1.12.1+cu113 on an RTX 3090.
Experiment Setup Yes Table 4: Hyperparameters for image classification experiments. HFlip denotes the classical horizontal flip. and General Considerations. Table 4 summarizes all the hyperparameters used in the paper for CIFAR-10 and CIFAR-100. In all cases, we use SGD combined with a multistep-learning-rate scheduler multiplying the rate by γ-lr at each milestone.