Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization
Authors: Xuefeng GAO, Mert Gurbuzbalaban, Lingjiong Zhu
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | On the bottom panel of Figure 1, we provide an example for training fully-connected neural networks on MNIST where ULD was faster when both methods were tuned. |
| Researcher Affiliation | Academia | Xuefeng Gao Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong... Mert Gürbüzbalaban Department of Management Science and Information Systems Rutgers Business School... Lingjiong Zhu Department of Mathematics Florida State University |
| Pseudocode | No | The paper describes algorithms using mathematical equations (e.g., (0.7)-(0.8)), but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statements about releasing code or links to source code repositories for the methodology described. |
| Open Datasets | Yes | On the bottom panel of Figure 1, we provide an example for training fully-connected neural networks on MNIST where ULD was faster when both methods were tuned. |
| Dataset Splits | No | The paper mentions using the MNIST dataset for numerical illustrations but does not provide specific details on training, validation, or test dataset splits (e.g., percentages, sample counts, or explicit standard splits). |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the numerical experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions) used for the numerical experiments. |
| Experiment Setup | No | The paper provides high-level parameter choices for the numerical illustrations (e.g., 'J is chosen randomly and γ = 2 m', 'when both methods were tuned'), but lacks specific experimental setup details such as concrete hyperparameter values (learning rate, batch size, number of epochs) or optimizer settings for the neural network training. |