Goto

Collaborating Authors

 imagenet dataset






Position-basedScaledGradientforModel QuantizationandPruning-Appendix

Neural Information Processing Systems

Inthis experiment, we only quantize the weights, not the activations, to compare the performance degradation as weight bit-width decreases. The mean squared errors (MSE) of the weights across different bit-widths are also reported. The name of the layer and the number of parameters in parenthesis are shown in the column. All numbers are results of the last epoch. Table A3: ResNet-32 trained with Adam on the CIFAR-100 dataset.




Fast Samplers for Inverse Problems in Iterative Refinement Models

Neural Information Processing Systems

Iterative refinement models, such as diffusion generative models and flow matching methods [Sohl-Dickstein et al., 2015, Ho et al., 2020, Song et al., 2020, Lipman et al., 2023, Albergo and V anden-Eijnden, 2023], have seen increasing popularity in recent months, and much effort has been invested