English
Related papers

Related papers: Implicit Reparameterization Gradients

200 papers

We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for the continuous latent variables, while performing exact…

Machine Learning · Computer Science 2020-02-12 Zhe Dong , Bryan A. Seybold , Kevin P. Murphy , Hung H. Bui

To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variable augmentation,…

Machine Learning · Statistics 2019-12-24 Mingzhang Yin , Yuguang Yue , Mingyuan Zhou

How to find flat minima? We propose running normalized gradient descent, usually reserved for nonsmooth optimization, with sufficiently slowly diminishing step sizes. This induces implicit regularization towards flat minima if an…

Optimization and Control · Mathematics 2026-02-10 Cédric Josz

Natural-gradient methods enable fast and simple algorithms for variational inference, but due to computational difficulties, their use is mostly limited to \emph{minimal} exponential-family (EF) approximations. In this paper, we extend…

Machine Learning · Statistics 2020-11-09 Wu Lin , Mohammad Emtiyaz Khan , Mark Schmidt

Works on implicit regularization have studied gradient trajectories during the optimization process to explain why deep networks favor certain kinds of solutions over others. In deep linear networks, it has been shown that gradient descent…

Machine Learning · Computer Science 2023-06-02 Dan Zhao

We propose using model reparametrization to improve variational Bayes inference for hierarchical models whose variables can be classified as global (shared across observations) or local (observation specific). Posterior dependence between…

Methodology · Statistics 2021-01-28 Linda S. L. Tan

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Wei Hu , Yuping Luo

Partitioning a set of elements into an unknown number of mutually exclusive subsets is essential in many machine learning problems. However, assigning elements, such as samples in a dataset or neurons in a network layer, to an unknown and…

Machine Learning · Computer Science 2023-11-10 Thomas M. Sutter , Alain Ryser , Joram Liebeskind , Julia E. Vogt

This study presents new closed-form estimators for the Dirichlet and the Multivariate Gamma distribution families, whose maximum likelihood estimator cannot be explicitly derived. The methodology builds upon the score-adjusted estimators…

Statistics Theory · Mathematics 2023-11-28 Ioannis Oikonomidis , Samis Trevezas

Many machine learning tasks require sampling a subset of items from a collection based on a parameterized distribution. The Gumbel-softmax trick can be used to sample a single item, and allows for low-variance reparameterized gradients with…

Machine Learning · Computer Science 2021-03-02 Sang Michael Xie , Stefano Ermon

We introduce iterative tilting, a gradient-free method for fine-tuning diffusion models toward reward-tilted distributions. The method decomposes a large reward tilt $\exp(\lambda r)$ into $N$ sequential smaller tilts, each admitting a…

Machine Learning · Statistics 2025-12-04 Jean Pachebat , Giovanni Conforti , Alain Durmus , Yazid Janati

Gradients have been exploited in proposal distributions to accelerate the convergence of Markov chain Monte Carlo algorithms on discrete distributions. However, these methods require a natural differentiable extension of the target discrete…

Machine Learning · Computer Science 2023-02-28 Yue Xiang , Dongyao Zhu , Bowen Lei , Dongkuan Xu , Ruqi Zhang

Discrete gradient methods are well-known methods of Geometric Numerical Integration, which preserve the dissipation of gradient systems. The preservation of the dissipation of a system is an important feature in numerous image processing…

Numerical Analysis · Mathematics 2016-03-25 V Grimm , R I McLachlan , D McLaren , G R W Quispel , C-B Schönlieb

Countless signal processing applications include the reconstruction of signals from few indirect linear measurements. The design of effective measurement operators is typically constrained by the underlying hardware and physics, posing a…

Machine Learning · Computer Science 2023-05-23 Jonathan Sauder , Martin Genzel , Peter Jung

We examine gradient descent on unregularized logistic regression problems, with homogeneous linear predictors on linearly separable datasets. We show the predictor converges to the direction of the max-margin (hard margin SVM) solution. The…

Machine Learning · Statistics 2024-10-29 Daniel Soudry , Elad Hoffer , Mor Shpigel Nacson , Suriya Gunasekar , Nathan Srebro

We propose graph-dependent implicit regularisation strategies for distributed stochastic subgradient descent (Distributed SGD) for convex problems in multi-agent learning. Under the standard assumptions of convexity, Lipschitz continuity,…

Machine Learning · Computer Science 2018-09-20 Dominic Richards , Patrick Rebeschini

We consider blind ptychography, an imaging technique which aims to reconstruct an object of interest from a set of its diffraction patterns, each obtained by a local illumination. As the distribution of the light within the illuminated…

Numerical Analysis · Mathematics 2023-06-16 Oleh Melnyk

Stein's method (Stein, 1973; 1981) is a powerful tool for statistical applications and has significantly impacted machine learning. Stein's lemma plays an essential role in Stein's method. Previous applications of Stein's lemma either…

Machine Learning · Statistics 2025-02-04 Wu Lin , Mohammad Emtiyaz Khan , Mark Schmidt

This paper presents enhancement strategies for the Hermitian and skew-Hermitian splitting method based on gradient iterations. The spectral properties are exploited for the parameter estimation, often resulting in a better convergence. In…

Numerical Analysis · Mathematics 2020-07-08 Qinmeng Zou , Frederic Magoules

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien
‹ Prev 1 3 4 5 6 7 10 Next ›