English
Related papers

Related papers: Active Slices for Sliced Stein Discrepancy

200 papers

Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the…

Machine Learning · Computer Science 2023-06-06 Amirhossein Reisizadeh , Haochuan Li , Subhro Das , Ali Jadbabaie

We propose a novel adaptive test of goodness-of-fit, with computational cost linear in the number of samples. We learn the test features that best indicate the differences between observed samples and a reference model, by minimizing the…

Machine Learning · Statistics 2017-10-25 Wittawat Jitkrittum , Wenkai Xu , Zoltan Szabo , Kenji Fukumizu , Arthur Gretton

Stein variational gradient decent (SVGD) has been shown to be a powerful approximate inference algorithm for complex distributions. However, the standard SVGD requires calculating the gradient of the target density and cannot be applied…

Machine Learning · Statistics 2018-06-08 Jun Han , Qiang Liu

Kernel-based online learning has often shown state-of-the-art performance for many online learning tasks. It, however, suffers from a major shortcoming, that is, the unbounded number of support vectors, making it non-scalable and unsuitable…

Machine Learning · Computer Science 2012-06-22 Peilin Zhao , Jialei Wang , Pengcheng Wu , Rong Jin , Steven C. H. Hoi

We propose an adaptive accelerated gradient method for solving smooth convex optimization problems. The method incorporates a scheme to determine the step size adaptively, by means of a local estimation of the smoothness constant, which is…

Optimization and Control · Mathematics 2025-12-24 Zepeng Wang , Juan Peypouquet

Stochastic gradient algorithms have been the main focus of large-scale learning problems and they led to important successes in machine learning. The convergence of SGD depends on the careful choice of learning rate and the amount of the…

Machine Learning · Computer Science 2015-11-03 Caglar Gulcehre , Marcin Moczulski , Yoshua Bengio

In distributed training of deep neural networks, people usually run Stochastic Gradient Descent (SGD) or its variants on each machine and communicate with other machines periodically. However, SGD might converge slowly in training some deep…

Machine Learning · Computer Science 2022-10-14 Mingrui Liu , Zhenxun Zhuang , Yunwei Lei , Chunyang Liao

It is well-known that the reparameterisation gradient estimator, which exhibits low variance in practice, is biased for non-differentiable models. This may compromise correctness of gradient-based optimisation methods such as stochastic…

Machine Learning · Computer Science 2024-02-21 Dominik Wagner , Basim Khajwal , C. -H. Luke Ong

Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of…

Machine Learning · Computer Science 2017-03-03 Caglar Gulcehre , Jose Sotelo , Marcin Moczulski , Yoshua Bengio

Stochastic gradient descent (SGD) gives an optimal convergence rate when minimizing convex stochastic objectives $f(x)$. However, in terms of making the gradients small, the original SGD does not give an optimal rate, even when $f(x)$ is…

Machine Learning · Computer Science 2021-07-30 Zeyuan Allen-Zhu

We establish optimal convergence rates for a decomposition-based scalable approach to kernel ridge regression. The method is simple to describe: it randomly partitions a dataset of size N into m subsets of equal size, computes an…

Statistics Theory · Mathematics 2014-05-01 Yuchen Zhang , John C. Duchi , Martin J. Wainwright

Stochastic Gradient Descent (SGD) is a popular tool in training large-scale machine learning models. Its performance, however, is highly variable, depending crucially on the choice of the step sizes. Accordingly, a variety of strategies for…

Machine Learning · Statistics 2021-06-11 Xiaoyu Li , Zhenxun Zhuang , Francesco Orabona

Modern large-scale kernel-based tests such as maximum mean discrepancy (MMD) and kernelized Stein discrepancy (KSD) optimize kernel hyperparameters on a held-out sample via data splitting to obtain the most powerful test statistics. While…

Machine Learning · Computer Science 2020-10-20 Jonas M. Kübler , Wittawat Jitkrittum , Bernhard Schölkopf , Krikamol Muandet

Accurate and efficient environment representation is crucial for robotic applications such as motion planning, manipulation, and navigation. Signed distance functions (SDFs) have emerged as a powerful representation for encoding distance to…

Robotics · Computer Science 2026-04-01 Zhirui Dai , Tianxing Fan , Mani Amani , Jaemin Seo , Ki Myung Brian Lee , Hyondong Oh , Nikolay Atanasov

Existing example-based prediction explanation methods often bridge test and training data points through the model's parameters or latent representations. While these methods offer clues to the causes of model predictions, they often…

Machine Learning · Computer Science 2025-05-20 Mahtab Sarvmaili , Hassan Sajjad , Ga Wu

Sliced Wasserstein distances preserve properties of classic Wasserstein distances while being more scalable for computation and estimation in high dimensions. The goal of this work is to quantify this scalability from three key aspects: (i)…

Machine Learning · Statistics 2022-10-18 Sloan Nietert , Ritwik Sadhu , Ziv Goldfeld , Kengo Kato

The general perception is that kernel methods are not scalable, and neural nets are the methods of choice for nonlinear learning problems. Or have we simply not tried hard enough for kernel methods? Here we propose an approach that scales…

Machine Learning · Computer Science 2015-09-11 Bo Dai , Bo Xie , Niao He , Yingyu Liang , Anant Raj , Maria-Florina Balcan , Le Song

Particle-based approximate Bayesian inference approaches such as Stein Variational Gradient Descent (SVGD) combine the flexibility and convergence guarantees of sampling methods with the computational benefits of variational inference. In…

Machine Learning · Computer Science 2021-07-30 Lauro Langosco di Langosco , Vincent Fortuin , Heiko Strathmann

The Wasserstein distance is a powerful metric based on the theory of optimal transport. It gives a natural measure of the distance between two distributions with a wide range of applications. In contrast to a number of the common…

Machine Learning · Computer Science 2021-02-16 Jung Hun Oh , Maryam Pouryahya , Aditi Iyer , Aditya P. Apte , Allen Tannenbaum , Joseph O. Deasy

While stochastic gradient descent (SGD) is still the most popular optimization algorithm in deep learning, adaptive algorithms such as Adam have established empirical advantages over SGD in some deep learning applications such as training…

Machine Learning · Computer Science 2023-06-02 Yan Pan , Yuanzhi Li
‹ Prev 1 3 4 5 6 7 10 Next ›