Gradient estimation of probabilistic programs reduces soundly to probabilistic inference after programmable coupling and factorization, enabling new low-variance estimators that beat baselines.
Discrete Variational Autoencoders
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We present a novel method to train a class of probabilistic models with discrete latent variables using the variational autoencoder framework, including backpropagation through the discrete latent variables. The associated class of probabilistic models comprises an undirected discrete component and a directed hierarchical continuous component. The discrete component captures the distribution over the disconnected smooth manifolds induced by the continuous component. As a result, this class of models efficiently learns both the class of objects in an image, and their specific realization in pixels, from unsupervised data, and outperforms state-of-the-art methods on the permutation-invariant MNIST, Omniglot, and Caltech-101 Silhouettes datasets.
citation-role summary
method 2
citation-polarity summary
roles
method 2representative citing papers
HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.
A multi-mode quantum annealing approach enables VAEs with Boltzmann priors, showing faster training and better generation than Gaussian-prior VAEs on MNIST, Fashion-MNIST, and CelebA plus improved out-of-distribution detection.
DSA adds a jointly trained confidence head to autoregressive video diffusion models that dynamically allocates fewer or more denoising steps per frame, achieving 22.63 FPS real-time generation on H100 while matching VBench quality.
Scaling an autoregressive Transformer to 20B parameters for text-to-image generation using image token sequences achieves new SOTA zero-shot FID of 7.23 and fine-tuned FID of 3.22 on MS-COCO.
Quantum annealing combined with a Neural Hash Function lets generative models create molecules that are more drug-like than classical versions or the training set itself.
A survey that categorizes deep learning models for point cloud tasks by backbone architecture, evaluates benchmark performance, and outlines challenges and future research directions.
citing papers explorer
-
GradInf: Gradient Estimation as Probabilistic Inference
Gradient estimation of probabilistic programs reduces soundly to probabilistic inference after programmable coupling and factorization, enabling new low-variance estimators that beat baselines.
-
Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.
-
Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors
A multi-mode quantum annealing approach enables VAEs with Boltzmann priors, showing faster training and better generation than Gaussian-prior VAEs on MNIST, Fashion-MNIST, and CelebA plus improved out-of-distribution detection.
-
DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation
DSA adds a jointly trained confidence head to autoregressive video diffusion models that dynamically allocates fewer or more denoising steps per frame, achieving 22.63 FPS real-time generation on H100 while matching VBench quality.
-
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Scaling an autoregressive Transformer to 20B parameters for text-to-image generation using image token sequences achieves new SOTA zero-shot FID of 7.23 and fine-tuned FID of 3.22 on MS-COCO.
-
Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer
Quantum annealing combined with a Neural Hash Function lets generative models create molecules that are more drug-like than classical versions or the training set itself.
-
A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation
A survey that categorizes deep learning models for point cloud tasks by backbone architecture, evaluates benchmark performance, and outlines challenges and future research directions.