Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees

Authors: Sean Jaffe, Alexander Davydov, Deniz Lapsekili, Ambuj K Singh, Francesco Bullo

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

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the performance of ELCD on the high dimensional LASA, multi-link pendulum, and Rosenbrock datasets.
Researcher Affiliation Academia 1 Center for Control, Dynamical Systems and Computation, University of California, Santa Barbara. 2 Department of Computer Science, University of California, Santa Barbara.
Pseudocode No The paper describes the proposed model and its components but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes The code for our model and data can be found here: https://github.com/seanjaffe1/Extended-Linearized-Contracting-Dynamics.
Open Datasets Yes We experiment with the LASA dataset [26]... Alongside the new ELCD model, we also provide the n-link pendulum dataset and Rosenbrock dataset in the supplementary material of the submission.
Dataset Splits No The paper states that "Each model is trained on all trajectories of the same dimension" but does not provide specific train/validation/test dataset splits (e.g., percentages or counts) for the datasets used.
Hardware Specification No All computation is done on CPUs. This statement is too general and does not provide specific CPU models, memory, or other detailed hardware specifications.
Software Dependencies No The paper mentions "Adam optimizer" and refers to "M-flow [8] code" but does not specify version numbers for these or other key software dependencies required for replication.
Experiment Setup Yes All experiments are trained with a batch size of 100, for 100 epochs, with an Adam optimizer and learning rate of 10 3.