paper-with-me

Papers

Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models

2022-09-11 · Pasquale Minervini, Luca Franceschi, Mathias Niepert

The integration of discrete algorithmic components in deep learning architectures has numerous applications. Recently, Implicit Maximum Likelihood Estimation (IMLE, Niepert, Minervini, and Franceschi 2021), a class of gradient estimators for discrete exponential family distributions, was proposed by combining implicit differentiation through perturbation with the path-wise gradient estimator. However, due to the finite difference approximation of the gradients, it is especially sensitive to the choice of the finite difference step size, which needs to be specified by the user. In this work, we present Adaptive IMLE (AIMLE), the first adaptive gradient estimator for complex discrete distributions: it adaptively identifies the target distribution for IMLE by trading off the density of gradient information with the degree of bias in the gradient estimates. We empirically evaluate our estimator on synthetic examples, as well as on Learning to Explain, Discrete Variational Auto-Encoders, and Neural Relational Inference tasks. In our experiments, we show that our adaptive gradient estimator can produce faithful estimates while requiring orders of magnitude fewer samples than other gradient estimators.

📄 PDF Abstract BibTeX arXiv:2209.04862

Code (1)

edinburghnlp/torch-adaptive-imle 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Adaptive system optimization using random directions stochastic approximation

2015-02-19 · Prashanth L. A., Shalabh Bhatnagar, Michael Fu, Steve Marcus

We present novel algorithms for simulation optimization using random directions stochastic approximation (RDSA). These include first-order (gradient) as well as second-order (Newton) schemes. We incorporate both continuo…

Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC

2017-06-06 · ICML 2017 8 · Yulai Cong, Bo Chen, Hongwei Liu, Mingyuan Zhou

It is challenging to develop stochastic gradient based scalable inference for deep discrete latent variable models (LVMs), due to the difficulties in not only computing the gradients, but also adapting the step sizes to …

Data Augmentation

Latent Transformations for Discrete-Data Normalising Flows

2020-06-11 · Rob Hesselink, Wilker Aziz

Normalising flows (NFs) for discrete data are challenging because parameterising bijective transformations of discrete variables requires predicting discrete/integer parameters. Having a neural network architecture predi…

Normalising Flows

Double Control Variates for Gradient Estimation in Discrete Latent Variable Models

2021-11-09 · pproximateinference AABI Symposium 2022 2 · Michalis K. Titsias, Jiaxin Shi

Stochastic gradient-based optimisation for discrete latent variable models is challenging due to the high variance of gradients. We introduce a variance reduction technique for score function estimators that makes use of…

Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping

2022-08-12 · Russell Z. Kunes, Mingzhang Yin, Max Land, Doron Haviv 외

Gradient estimation is often necessary for fitting generative models with discrete latent variables, in contexts such as reinforcement learning and variational autoencoder (VAE) training. The DisARM estimator (Yin et al.…