8 papers
Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
Tianyu Xie, Shuchen Xue, Zijin Feng +4
Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality…
Importance Weighted Variational Inference without the Reparameterization Trick
Kamélia Daudel, Minh-Ngoc Tran, Cheng Zhang
Importance weighted variational inference (VI) approximates densities known up to a normalizing constant by optimizing bounds that tighten with the number of Monte Carlo samples $N…
A Kernel Approach for Semi-implicit Variational Inference
Longlin Yu, Ziheng Cheng, Shiyue Zhang +1
Semi-implicit variational inference (SIVI) enhances the expressiveness of variational families through hierarchical semi-implicit distributions, but the intractability of their den…
Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
Ziheng Cheng, Tianyu Xie, Shiyue Zhang +1
While conditional diffusion models have achieved remarkable success in various applications, they require abundant data to train from scratch, which is often infeasible in practice…
Continuous Semi-Implicit Models
Longlin Yu, Jiajun Zha, Tong Yang +4
Semi-implicit distributions have shown great promise in variational inference and generative modeling. Hierarchical semi-implicit models, which stack multiple semi-implicit layers,…
Semi-Implicit Functional Gradient Flow for Efficient Sampling
Shiyue Zhang, Ziheng Cheng, Cheng Zhang
Particle-based variational inference methods (ParVIs) use nonparametric variational families represented by particles to approximate the target distribution according to the kernel…