Lie Group Decompositions for Equivariant Neural Networks

Authors: Mircea Mironenco, Patrick Forré

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the robustness and out-of-distribution generalisation capability of our model on the benchmark affine-invariant classification task, outperforming previous proposals. ... For all experiments we use a Res Net-style architecture...
Researcher Affiliation Academia Mircea Mironenco AI4Science Lab, AMLab Informatics Institute University of Amsterdam mircea.mironenco@gmail.com Patrick Forr e AI4Science Lab, AMLab Informatics Institute University of Amsterdam p.d.forre@uva.nl
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Our code is publicly available at https://github.com/mirceamironenco/rgenn.
Open Datasets Yes We evaluate our model on a benchmark affine-invariant image classification task employing the aff NIST dataset2. ... The experimental setup involves training on the standard set of 50000 non-transformed MNIST images (padded to 40 40)...
Dataset Splits No The paper mentions training and test sets but does not provide specific details about a validation dataset split or how it was used.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models used for running the experiments.
Software Dependencies No The paper mentions specific software components like "Adam optimizer" and "SIREN networks" but does not provide their specific version numbers.
Experiment Setup Yes All experiments will use the same Res Net-like architecture He et al. (2016)... We set ω0 = 10 for all experiments. We use 42 output channels in both the lifting and cross-correlation layers. Each SIREN network consists of 2 layers of size 60. ... The models are trained for 100 epochs, with a batch size of 128, and the Adam optimizer of Kingma & Ba (2014) with a standard learning rate of 0.0001.