English
Related papers

Related papers: Implicit Reparameterization Gradients

200 papers

Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used throughout machine and reinforcement learning; however, they are usually explained as simple mathematical tricks without providing any insight into their nature.…

Machine Learning · Computer Science 2019-10-16 Paavo Parmas , Masashi Sugiyama

We study the foundations of variational inference, which frames posterior inference as an optimisation problem, for probabilistic programming. The dominant approach for optimisation in practice is stochastic gradient descent. In particular,…

Programming Languages · Computer Science 2023-01-10 Basim Khajwal , C. -H. Luke Ong , Dominik Wagner

Reparameterizable densities are an important way to learn probability distributions in a deep learning setting. For many distributions it is possible to create low-variance gradient estimators by utilizing a `reparameterization trick'. Due…

Machine Learning · Statistics 2019-03-13 Luca Falorsi , Pim de Haan , Tim R. Davidson , Patrick Forré

Many statistical estimators for high-dimensional linear regression are M-estimators, formed through minimizing a data-dependent square loss function plus a regularizer. This work considers a new class of estimators implicitly defined…

Statistics Theory · Mathematics 2022-02-15 Peng Zhao , Yun Yang , Qiao-Chu He

Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate (low bias) gradient estimator is crucial to face…

Machine Learning · Computer Science 2022-03-09 Joao Carvalho , Jan Peters

Gradient estimation -- approximating the gradient of an expectation with respect to the parameters of a distribution -- is central to the solution of many machine learning problems. However, when the distribution is discrete, most common…

Machine Learning · Statistics 2024-04-16 Jiaxin Shi , Yuhao Zhou , Jessica Hwang , Michalis K. Titsias , Lester Mackey

Learning in models with discrete latent variables is challenging due to high variance gradient estimators. Generally, approaches have relied on control variates to reduce the variance of the REINFORCE estimator. Recent work (Jang et al.…

Machine Learning · Computer Science 2017-11-07 George Tucker , Andriy Mnih , Chris J. Maddison , Dieterich Lawson , Jascha Sohl-Dickstein

Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used to estimate gradients of expectations throughout machine learning and reinforcement learning; however, they are usually explained as simple mathematical tricks,…

Machine Learning · Computer Science 2021-06-01 Paavo Parmas , Masashi Sugiyama

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

Machine Learning · Computer Science 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameters and a random…

Machine Learning · Computer Science 2017-03-07 Chris J. Maddison , Andriy Mnih , Yee Whye Teh

Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training. However, there exists a gap in understanding how…

Machine Learning · Computer Science 2023-03-08 Alexander Detkov , Mohammad Salameh , Muhammad Fetrat Qharabagh , Jialin Zhang , Wei Lui , Shangling Jui , Di Niu

We introduce a family of pairwise stochastic gradient estimators for gradients of expectations, which are related to the log-derivative trick, but involve pairwise interactions between samples. The simplest example of our new estimator,…

Machine Learning · Computer Science 2022-04-21 Christian J. Walder , Paul Roussel , Richard Nock , Cheng Soon Ong , Masashi Sugiyama

Categorical random variables can faithfully represent the discrete and uncertain aspects of data as part of a discrete latent variable model. Learning in such models necessitates taking gradients with respect to the parameters of the…

Machine Learning · Computer Science 2023-11-22 Lennert De Smet , Emanuele Sansone , Pedro Zuidberg Dos Martires

Variational approximations are increasingly based on gradient-based optimization of expectations estimated by sampling. Handling discrete latent variables is then challenging because the sampling process is not differentiable. Continuous…

Machine Learning · Computer Science 2021-02-09 Tomasz Kuśmierczyk , Arto Klami

We propose a simple and general variant of the standard reparameterized gradient estimator for the variational evidence lower bound. Specifically, we remove a part of the total derivative with respect to the variational parameters that…

Machine Learning · Statistics 2017-05-30 Geoffrey Roeder , Yuhuai Wu , David Duvenaud

Stochastic gradient descent procedures have gained popularity for parameter estimation from large data sets. However, their statistical properties are not well understood, in theory. And in practice, avoiding numerical instability requires…

Methodology · Statistics 2016-09-29 Panos Toulis , Edoardo M. Airoldi

Training models with discrete latent variables is challenging due to the high variance of unbiased gradient estimators. While low-variance reparameterization gradients of a continuous relaxation can provide an effective solution, a…

Machine Learning · Computer Science 2022-11-16 Zhe Dong , Andriy Mnih , George Tucker

Gradient regularization (GR) is a method that penalizes the gradient norm of the training loss during training. While some studies have reported that GR can improve generalization performance, little attention has been paid to it from the…

Machine Learning · Computer Science 2023-02-06 Ryo Karakida , Tomoumi Takase , Tomohiro Hayase , Kazuki Osawa

In many applications we seek to maximize an expectation with respect to a distribution over discrete variables. Estimating gradients of such objectives with respect to the distribution parameters is a challenging problem. We analyze…

Machine Learning · Statistics 2019-06-18 Evgeny Andriyash , Arash Vahdat , Bill Macready

Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems. Due to the highly nonconvex nature of the empirical loss, state-of-the-art procedures often…

Machine Learning · Computer Science 2020-06-09 Cong Ma , Kaizheng Wang , Yuejie Chi , Yuxin Chen