English
Related papers

Related papers: Implicit Reparameterization Gradients

200 papers

We present and analyze several strategies for improving the performance of stochastic variance-reduced gradient (SVRG) methods. We first show that the convergence rate of these methods can be preserved under a decreasing sequence of errors…

Machine Learning · Computer Science 2016-08-06 Reza Babanezhad , Mohamed Osama Ahmed , Alim Virani , Mark Schmidt , Jakub Konečný , Scott Sallinen

For infinitesimal learning rates, stochastic gradient descent (SGD) follows the path of gradient flow on the full batch loss function. However moderately large learning rates can achieve higher test accuracies, and this generalization…

Machine Learning · Computer Science 2021-01-29 Samuel L. Smith , Benoit Dherin , David G. T. Barrett , Soham De

Preconditioned gradient iterations for very large eigenvalue problems are efficient solvers with growing popularity. However, only for the simplest preconditioned eigensolver, namely the preconditioned gradient iteration (or preconditioned…

Numerical Analysis · Mathematics 2011-08-12 Klaus Neymeyr

We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious…

Machine Learning · Computer Science 2021-11-05 Da Yu , Huishuai Zhang , Wei Chen , Jian Yin , Tie-Yan Liu

Meta-learning owns unique effectiveness and swiftness in tackling emerging tasks with limited data. Its broad applicability is revealed by viewing it as a bi-level optimization problem. The resultant algorithmic viewpoint however, faces…

Machine Learning · Computer Science 2023-12-22 Yilang Zhang , Bingcong Li , Shijian Gao , Georgios B. Giannakis

Probabilistic programming has emerged as a powerful paradigm in statistics, applied science, and machine learning: by decoupling modelling from inference, it promises to allow modellers to directly reason about the processes generating…

Machine Learning · Statistics 2019-06-10 Maria I. Gorinova , Dave Moore , Matthew D. Hoffman

This paper deals with the problem of outliers in high frequency observation data from diffusion processes. Robust estimation methods are needed because the inclusion of outliers can lead to incorrect statistical inference even in the…

Methodology · Statistics 2026-03-06 Tomoyuki Nakagawa , Yusuke Shimizu

While stochastic variational inference is relatively well known for scaling inference in Bayesian probabilistic models, related methods also offer ways to circumnavigate the approximation of analytically intractable expectations. The key…

Machine Learning · Statistics 2015-09-08 David A. Knowles

This paper explores variants of the subspace iteration algorithm for computing approximate invariant subspaces. The standard subspace iteration approach is revisited and new variants that exploit gradient-type techniques combined with a…

Numerical Analysis · Mathematics 2024-05-14 Foivos Alimisis , Yousef Saad , Bart Vandereycken

First-order optimization methods tend to inherently favor certain solutions over others when minimizing an underdetermined training objective that has multiple global optima. This phenomenon, known as implicit bias, plays a critical role in…

Machine Learning · Computer Science 2024-04-09 Guanghui Wang , Zihao Hu , Claudio Gentile , Vidya Muthukumar , Jacob Abernethy

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model…

Machine Learning · Computer Science 2026-05-01 Nghia Bui , Lijing Wang

Setting regularization parameters for Lasso-type estimators is notoriously difficult, though crucial in practice. The most popular hyperparameter optimization approach is grid-search using held-out validation data. Grid-search however…

Envelope models provide a sufficient dimension reduction framework for multivariate regression analysis. Bayesian inference for these models has been developed primarily using Markov chain Monte Carlo (MCMC) methods. Specifically, Gibbs…

Methodology · Statistics 2026-03-03 Seunghyeon Kim , Kwangmin Lee , Yeonhee Park

In order to develop a differential calculus for error propagation we study local Dirichlet forms on probability spaces with square field operator $\Gamma$ -- i.e. error structures -- and we are looking for an object related to $\Gamma$…

Probability · Mathematics 2007-05-23 Nicolas Bouleau

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 double control…

Machine Learning · Statistics 2022-06-07 Michalis K. Titsias , Jiaxin Shi

We investigate a local reparameterizaton technique for greatly reducing the variance of stochastic gradients for variational Bayesian inference (SGVB) of a posterior over model parameters, while retaining parallelizability. This local…

Machine Learning · Statistics 2015-12-22 Diederik P. Kingma , Tim Salimans , Max Welling

The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to large combinatorial distributions is still outstanding. Working…

Machine Learning · Statistics 2021-03-02 Max B. Paulus , Dami Choi , Daniel Tarlow , Andreas Krause , Chris J. Maddison

We propose an algorithm for inexpensive gradient-based hyperparameter optimization that combines the implicit function theorem (IFT) with efficient inverse Hessian approximations. We present results about the relationship between the IFT…

Machine Learning · Computer Science 2019-11-11 Jonathan Lorraine , Paul Vicol , David Duvenaud

Gradient estimation is a central challenge in training parameterized quantum circuits (PQCs) for hybrid quantum-classical optimization and learning problems. This difficulty arises from several factors, including the exponential…

Quantum Physics · Physics 2026-05-25 Mohsen Heidari , Masih Mozakka , Wojciech Szpankowski

Projected gradient descent and its Riemannian variant belong to a typical class of methods for low-rank matrix estimation. This paper proposes a new Nesterov's Accelerated Riemannian Gradient algorithm by efficient orthographic retraction…

Optimization and Control · Mathematics 2023-06-05 Hongyi Li , Zhen Peng , Chengwei Pan , Di Zhao