English
Russian
French
Spanish
German
Japanese
korean
PortugueseNews
How Fast Is PyJuice? Testing Compilation Speed Across GPUs and Batch Sizes
This article presents experimental benchmarks for PyJuice, highlighting its efficiency in both compilation and runtime. Tests show...
The Future of Tractable Deep Generative Models
PyJuice is a new system for training and inference of probabilistic circuits that outperforms prior baselines in speed, memory eff...
PyJuice Pushes HMMs and Image Models Beyond State-of-the-Art
PyJuice dramatically accelerates the training and inference of probabilistic circuits (PCs), outperforming established frameworks...
Optimizing Backpropagation with PC Flows
PyJuice introduces a highly efficient way to train probabilistic circuit (PC) models by optimizing backpropagation and reducing GP...
How Block-Based Parallelization Cuts IO and Computation Overhead
This article explores how block-based parallelization improves the efficiency of probabilistic circuits by reducing both IO and co...
Key Bottlenecks in PC Parallelization
This article examines the major bottlenecks in parallelizing probabilistic circuits (PCs), focusing on the forward pass. While pro...
Why Researchers Are Betting on PCs to Power the Next Wave of AI
Probabilistic Circuits (PCs) offer a unified framework for tractable probability distributions, enabling efficient probabilistic i...
