Neural Information Processing Systems http://nips.cc/

Due to the increasingly large size of datasets and high model complexity, direct minimisation of the regularised problem is posing more and morecomputationalchallenges.

To address this issue, we present the first analysis for instance weighting transfer learning that considers the presence of labeled target examples. The contribution of our work is two-fold.1. We address the question ofhow to measure the divergence between two domains given label informationforthetargetdomain.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Therefore, forasource task withacomplexmodel orfewtraining samples, even though itis similar to the target task, the knowledge transferable from this source task can still be verylimited.

However, functions on such complex objects (e.g., point sets and graphs) are often

In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of the latent space is empirically pivotal, determining the optimal choice and the process of identifying it remain unclear. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity. Our investigation starts with the classic generative adversarial networks (GANs). Inspired by the GAN training objective, we propose a novel distance between the latent and data distributions, whose minimization coincides with that of the generator complexity. The minimizer of this distance is characterized as the optimal data-dependent latent that most effectively capitalizes on the generator's capacity. Then, we consider parameterizing such a latent distribution by an encoder network and propose a two-stage training strategy called Decoupled Autoencoder (DAE), where the encoder is only updated in the first stage with an auxiliary decoder and then frozen in the second stage while the actual decoder is being trained. DAE can improve the latent distribution and as a result, improve the generative performance. Our theoretical analyses are corroborated by comprehensive experiments on various models such as VQGAN and Diffusion Transformer, where our modifications yield significant improvements in sample quality with decreased model complexity.