Automatic Symmetry Discovery with Lie Algebra Convolutional Network
Authors: Nima Dehmamy, Robin Walters, Yanchen Liu, Dashun Wang, Rose Yu
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conducted small controlled experiments to verify how multilayer L-conv approximates G-conv (SI C). We conducted experiments to learn large rotation angle between two images (SI C), shown in Fig. 4. We validated that L-conv can learn the correct Lie algebra basis in a synthetic experiment. |
| Researcher Affiliation | Academia | Nima Dehmamy Northwestern University nimadt@bu.edu Robin Walters Northeastern University rwalters@northeastern.edu Yanchen Liu Northeastern University liu.yanc@northeastern.edu Dashun Wang Northwestern University dashun.wang@kellogg.northwestern.edu Rose Yu University of California San Diego roseyu@ucsd.edu |
| Pseudocode | No | The paper describes the model and its implementation using mathematical equations and textual explanations, but it does not include a dedicated pseudocode or algorithm block. |
| Open Source Code | Yes | 1Code: github.com/nimadehmamy/L-conv-code |
| Open Datasets | No | The paper refers to 'small image datasets' (SI D) and generating '7x7 random images' (SI C) for experiments. While the checklist indicates data is provided for reproduction, the main paper does not provide concrete access information (links, citations) for a publicly available dataset itself. |
| Dataset Splits | No | The paper's main text does not explicitly provide numerical details on training, validation, or test dataset splits. It refers to supplemental information for experimental details (SI C, SI D), and the checklist affirms that training details are specified, but these details are not in the provided main text. |
| Hardware Specification | No | The main paper does not specify the exact hardware used for experiments (e.g., GPU/CPU models, memory, or specific cloud providers). While the checklist indicates this information is provided, it is not found within the main text. |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies (e.g., programming languages, libraries, or frameworks) used in the experiments. |
| Experiment Setup | No | The main paper does not explicitly detail the experimental setup, such as specific hyperparameter values (e.g., learning rate, batch size) or training configurations. This information is likely in the supplemental material. |