English
Related papers

Related papers: Implicit Reparameterization Gradients

200 papers

This paper aims at achieving a "good" estimator for the gradient of a function on a high-dimensional space. Often such functions are not sensitive in all coordinates and the gradient of the function is almost sparse. We propose a method for…

Machine Learning · Statistics 2016-07-27 Vivek S. Borkar , Vikranth R. Dwaracherla , Neeraja Sahasrabudhe

Sharpness-aware minimization (SAM) aims to improve the generalisation of gradient-based learning by seeking out flat minima. In this work, we establish connections between SAM and Mean-Field Variational Inference (MFVI) of neural network…

Machine Learning · Statistics 2022-10-20 Szilvia Ujváry , Zsigmond Telek , Anna Kerekes , Anna Mészáros , Ferenc Huszár

Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Dmitry Baranchuk , Ivan Rubachev , Andrey Voynov , Valentin Khrulkov , Artem Babenko

Softmax is widely used in neural networks for multiclass classification, gate structure and attention mechanisms. The statistical assumption that the input is normal distributed supports the gradient stability of Softmax. However, when used…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Shulun Wang , Bin Liu , Feng Liu

Differential equations are used to model and predict the behaviour of complex systems in a wide range of fields, and the ability to solve them is an important asset for understanding and predicting the behaviour of these systems.…

Machine Learning · Computer Science 2023-01-31 Siddharth Nand , Yuecheng Cai

Many optimization methods for training variational quantum algorithms are based on estimating gradients of the cost function. Due to the statistical nature of quantum measurements, this estimation requires many circuit evaluations, which is…

Quantum Physics · Physics 2022-10-14 Lennart Bittel , Jens Watty , Martin Kliesch

Bayesian inference for models with intractable likelihoods, such as Markov random fields, poses a fundamental computational challenge due to the tradeoff between inferential accuracy and computational cost. Various MCMC methods have been…

Methodology · Statistics 2026-04-01 Laura Bazahica , Alejandra Avalos-Pacheco , Matthew Moores , Lassi Roininen

Gradient boosting is a prediction method that iteratively combines weak learners to produce a complex and accurate model. From an optimization point of view, the learning procedure of gradient boosting mimics a gradient descent on a…

Machine Learning · Computer Science 2022-11-30 Erwan Fouillen , Claire Boyer , Maxime Sangnier

Deep learning has revolutionized industries like computer vision, natural language processing, and speech recognition. However, back propagation, the main method for training deep neural networks, faces challenges like computational…

Machine Learning · Computer Science 2023-08-15 Gokulprasath R

Inverse problems have many applications in science and engineering. In Computer vision, several image restoration tasks such as inpainting, deblurring, and super-resolution can be formally modeled as inverse problems. Recently, methods have…

Computer Vision and Pattern Recognition · Computer Science 2024-09-19 Sai Bharath Chandra Gutha , Ricardo Vinuesa , Hossein Azizpour

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by…

Machine Learning · Statistics 2020-08-28 Tomas Vaškevičius , Varun Kanade , Patrick Rebeschini

$k$-subset sampling is ubiquitous in machine learning, enabling regularization and interpretability through sparsity. The challenge lies in rendering $k$-subset sampling amenable to end-to-end learning. This has typically involved relaxing…

Machine Learning · Computer Science 2024-06-10 Kareem Ahmed , Zhe Zeng , Mathias Niepert , Guy Van den Broeck

In this paper, we consider gradient methods for minimizing smooth convex functions, which employ the information obtained at the previous iterations in order to accelerate the convergence towards the optimal solution. This information is…

Optimization and Control · Mathematics 2021-06-02 Yurii Nesterov , Mihai I. Florea

We derive and present explicit algorithms to facilitate streamlined computing for variational inference for models containing higher level random effects. Existing literature, such as Lee and Wand (2016), is such that streamlined…

Computation · Statistics 2020-07-07 Tui H. Nolan , Marianne Menictas , Matt P. Wand

Several recent works demonstrate that transformers can implement algorithms like gradient descent. By a careful construction of weights, these works show that multiple layers of transformers are expressive enough to simulate iterations of…

Machine Learning · Computer Science 2023-11-13 Kwangjun Ahn , Xiang Cheng , Hadi Daneshmand , Suvrit Sra

We construct a new kind of encoder, leveraging the expressive power of diffusion models. In a traditional variational autoencoder, the encoder and decoder jointly negotiate a latent representation of the input. This is made possible by the…

Machine Learning · Computer Science 2026-05-14 Akhil Premkumar , Sarah Lucioni

Derivative-based algorithms are ubiquitous in statistics, machine learning, and applied mathematics. Automatic differentiation offers an algorithmic way to efficiently evaluate these derivatives from computer programs that execute relevant…

Computation · Statistics 2022-03-01 Charles C. Margossian , Michael Betancourt

The reciprocal square root is an important computation for which many very sophisticated algorithms exist (see for example \cite{863046,863031} and the references therein). In this paper we develop a simple differential compensation (much…

Numerical Analysis · Mathematics 2021-06-14 Carlos F. Borges

We propose a new way of training neural networks, with the goal of reducing training cost. Our method uses approximate predicted gradients instead of the full gradients that require an expensive backward pass. We derive a…

Machine Learning · Computer Science 2025-11-10 Kamil Ciosek , Nicolò Felicioni , Juan Elenter Litwin

Sampling is an important tool for estimating large, complex sums and integrals over high dimensional spaces. For instance, important sampling has been used as an alternative to exact methods for inference in belief networks. Ideally, we…

Artificial Intelligence · Computer Science 2013-01-18 Luis E. Ortiz , Leslie Pack Kaelbling