On Calibrating Diffusion Probabilistic Models

Authors: Tianyu Pang, Cheng Lu, Chao Du, Min Lin, Shuicheng Yan, Zhijie Deng

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

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct experiments on multiple datasets to empirically validate our proposal.
Researcher Affiliation Collaboration 1Sea AI Lab, Singapore 2Department of Computer Science, Tsinghua University 3Qing Yuan Research Institute, Shanghai Jiao Tong University
Pseudocode No No pseudocode or algorithm blocks are provided in the main text or appendices.
Open Source Code Yes Our code is available at https://github.com/thudzj/Calibrated-DPMs.
Open Datasets Yes We evaluate our calibration tricks on the CIFAR-10 [25] and Celeb A 64 64 [27] datasets
Dataset Splits No The paper refers to using "training data" but does not provide specific train/validation/test splits (percentages, counts, or citations to predefined splits).
Hardware Specification No The paper does not provide specific details on the hardware used for running experiments (e.g., GPU/CPU models, memory, or cloud instances).
Software Dependencies No The paper mentions software like PyTorch and Tensorflow checkpoints, and the Adam optimizer, but does not specify their version numbers or other software dependencies with explicit versions.
Experiment Setup Yes In accordance with the recommendation, we set the end time of DPM-Solver to 10 3 when the number of sampling steps is less than 15, and to 10 4 otherwise. Additional details can be found in Lu et al. [29].