no code implementations • 2 May 2022 • Wonho Bae, Junhyug Noh, Milad Jalali Asadabadi, Danica J. Sutherland
Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels.
1 code implementation • ICLR 2022 • Yi Ren, Shangmin Guo, Danica J. Sutherland
Observing the learning path not only provides a new perspective for understanding knowledge distillation, overfitting, and learning dynamics, but also reveals that the supervisory signal of a teacher network can be very unstable near the best points in training on real tasks.
no code implementations • 8 Dec 2021 • Lijia Zhou, Frederic Koehler, Danica J. Sutherland, Nathan Srebro
We study a localized notion of uniform convergence known as an "optimistic rate" (Panchenko 2002; Srebro et al. 2010) for linear regression with Gaussian data.
no code implementations • NeurIPS 2021 • Frederic Koehler, Lijia Zhou, Danica J. Sutherland, Nathan Srebro
We consider interpolation learning in high-dimensional linear regression with Gaussian data, and prove a generic uniform convergence guarantee on the generalization error of interpolators in an arbitrary hypothesis class in terms of the class's Gaussian width.
1 code implementation • NeurIPS 2021 • Yazhe Li, Roman Pogodin, Danica J. Sutherland, Arthur Gretton
We approach self-supervised learning of image representations from a statistical dependence perspective, proposing Self-Supervised Learning with the Hilbert-Schmidt Independence Criterion (SSL-HSIC).
1 code implementation • NeurIPS 2021 • Feng Liu, Wenkai Xu, Jie Lu, Danica J. Sutherland
In realistic scenarios with very limited numbers of data samples, however, it can be challenging to identify a kernel powerful enough to distinguish complex distributions.
no code implementations • NeurIPS 2021 • Frederic Koehler, Lijia Zhou, Danica J. Sutherland, Nathan Srebro
We consider interpolation learning in high-dimensional linear regression with Gaussian data, and prove a generic uniform convergence guarantee on the generalization error of interpolators in an arbitrary hypothesis class in terms of the class’s Gaussian width.
no code implementations • 4 Jan 2021 • Pritish Kamath, Akilesh Tangella, Danica J. Sutherland, Nathan Srebro
We show that the Invariant Risk Minimization (IRM) formulation of Arjovsky et al. (2019) can fail to capture "natural" invariances, at least when used in its practical "linear" form, and even on very simple problems which directly follow the motivating examples for IRM.
no code implementations • NeurIPS 2020 • Lijia Zhou, Danica J. Sutherland, Nathan Srebro
But we argue we can explain the consistency of the minimal-norm interpolator with a slightly weaker, yet standard, notion: uniform convergence of zero-error predictors in a norm ball.
1 code implementation • ICML 2020 • Feng Liu, Wenkai Xu, Jie Lu, Guangquan Zhang, Arthur Gretton, Danica J. Sutherland
We propose a class of kernel-based two-sample tests, which aim to determine whether two sets of samples are drawn from the same distribution.
Ranked #1 on
Two-sample testing
on HIGGS Data Set
no code implementations • 5 Jun 2019 • Danica J. Sutherland
The maximum mean discrepancy (MMD) is a kernel-based distance between probability distributions useful in many applications (Gretton et al. 2012), bearing a simple estimator with pleasing computational and statistical properties.
1 code implementation • 20 Nov 2018 • Li Wenliang, Danica J. Sutherland, Heiko Strathmann, Arthur Gretton
The kernel exponential family is a rich class of distributions, which can be fit efficiently and with statistical guarantees by score matching.
1 code implementation • NeurIPS 2018 • Michael Arbel, Danica J. Sutherland, Mikołaj Bińkowski, Arthur Gretton
We propose a principled method for gradient-based regularization of the critic of GAN-like models trained by adversarially optimizing the kernel of a Maximum Mean Discrepancy (MMD).
Ranked #74 on
Image Generation
on CIFAR-10
4 code implementations • ICLR 2018 • Mikołaj Bińkowski, Danica J. Sutherland, Michael Arbel, Arthur Gretton
We investigate the training and performance of generative adversarial networks using the Maximum Mean Discrepancy (MMD) as critic, termed MMD GANs.
1 code implementation • 23 May 2017 • Danica J. Sutherland, Heiko Strathmann, Michael Arbel, Arthur Gretton
We propose a fast method with statistical guarantees for learning an exponential family density model where the natural parameter is in a reproducing kernel Hilbert space, and may be infinite-dimensional.
1 code implementation • 11 May 2017 • Ho Chung Leon Law, Danica J. Sutherland, Dino Sejdinovic, Seth Flaxman
Distribution regression has recently attracted much interest as a generic solution to the problem of supervised learning where labels are available at the group level, rather than at the individual level.
no code implementations • 9 Feb 2017 • Danica J. Sutherland
The seminal paper of Caponnetto and de Vito (2007) provides minimax-optimal rates for kernel ridge regression in a very general setting.
1 code implementation • 14 Nov 2016 • Danica J. Sutherland, Hsiao-Yu Tung, Heiko Strathmann, Soumyajit De, Aaditya Ramdas, Alex Smola, Arthur Gretton
In this context, the MMD may be used in two roles: first, as a discriminator, either directly on the samples, or on features of the samples.
1 code implementation • 11 Nov 2016 • Seth Flaxman, Danica J. Sutherland, Yu-Xiang Wang, Yee Whye Teh
We combine fine-grained spatially referenced census data with the vote outcomes from the 2016 US presidential election.
no code implementations • 13 Nov 2015 • Junier B. Oliva, Danica J. Sutherland, Barnabás Póczos, Jeff Schneider
The use of distributions and high-level features from deep architecture has become commonplace in modern computer vision.
no code implementations • 24 Sep 2015 • Danica J. Sutherland, Junier B. Oliva, Barnabás Póczos, Jeff Schneider
This work develops the first random features for pdfs whose dot product approximates kernels using these non-Euclidean metrics, allowing estimators using such kernels to scale to large datasets by working in a primal space, without computing large Gram matrices.
no code implementations • 1 Feb 2012 • Danica J. Sutherland, Liang Xiong, Barnabás Póczos, Jeff Schneider
Most machine learning algorithms, such as classification or regression, treat the individual data point as the object of interest.