Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer

Authors: Eric Qu, Xufang Luo, Dongsheng Li

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on various tasks demonstrate that altering data continuity via Lipschitz Regularizer can largely improve the performance of many deep models for sequence modeling.1
Researcher Affiliation Collaboration Eric Qu Duke Kunshan University Kunshan, Jiangsu 215316, China zhonghang.qu@duke.edu Xufang Luo & Dongsheng Li Microsoft Research Asia Shanghai 200232, China {xufluo, dongsheng.li}@microsoft.com
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes 1Code is available at https://Eric Qu.site/Lip Reg/
Open Datasets Yes We use 5 datasets in this experiment and their descriptions are in Appendix C.1. Evaluation metrics are Mean Square Error (MSE) and Mean Absolute Error (MAE).
Dataset Splits Yes Hyperparameter λ is chosen from {1, 2, 3, 4, 5} when the model performs best on the validation set.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup Yes Hyperparameter λ is chosen from {1, 2, 3, 4, 5} when the model performs best on the validation set. Hyperparameter λ is chosen from {1, 2, 3, 4, 5, 6, 7, 8} when the model performs best on the validation set.