paper-with-me

Papers

Learning in Integer Latent Variable Models with Nested Automatic Differentiation

2018-06-08 · ICML 2018 7 · Daniel Sheldon, Kevin Winner, Debora Sujono

We develop nested automatic differentiation (AD) algorithms for exact inference and learning in integer latent variable models. Recently, Winner, Sujono, and Sheldon showed how to reduce marginalization in a class of integer latent variable models to evaluating a probability generating function which contains many levels of nested high-order derivatives. We contribute faster and more stable AD algorithms for this challenging problem and a novel algorithm to compute exact gradients for learning. These contributions lead to significantly faster and more accurate learning algorithms, and are the first AD algorithms whose running time is polynomial in the number of levels of nesting.

📄 PDF Abstract BibTeX arXiv:1806.03207

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Automatic Laplace Collapsed Sampling: Scalable Marginalisation of Latent Parameters via Automatic Differentiation

2026-03-27 · Toby Lovick, David Yallup, Will Handley arxiv

We present Automatic Laplace Collapsed Sampling (ALCS), a general framework for marginalising latent parameters in Bayesian models using automatic differentiation, which we combine with nested sampling to explore the hyp…

Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training

2022-09-22 · Cong Guo, Yuxian Qiu, Jingwen Leng, Chen Zhang 외

An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN). Many novel and sophisticated activation functions have been proposed to improve the DNN accuracy but…

Generalized Nested Latent Variable Models for Lossy Coding applied to Wind Turbine Scenarios

2024-06-10 · Raül Pérez-Gonzalo, Andreas Espersen, Antonio Agudo

Rate-distortion optimization through neural networks has accomplished competitive results in compression efficiency and image quality. This learning-based approach seeks to minimize the compromise between compression rat…

Collapsing Taylor Mode Automatic Differentiation

2025-05-19 · Felix Dangel, Tim Siebert, Marius Zeinhofer, Andrea Walther

Computing partial differential equation (PDE) operators via nested backpropagation is expensive, yet popular, and severely restricts their utility for scientific machine learning. Recent advances, like the forward Laplac…

Archimedean Copula Inference via Taylor-Mode AD

2026-05-22 · Cambridge Yang, Dongdong Li arxiv

No existing nested Archimedean copula tool handles all three of (a) arbitrary per-variable (right-)censoring in survival analysis, (b) arbitrary nesting trees, and (c) exact parameter gradients. Existing implementations …