Oceania
Learning to Screen
Alon Cohen, Avinatan Hassidim, Haim Kaplan, Yishay Mansour, Shay Moran
Neural Information Processing Systems http://nips.cc/
class distribution is shared across datasets. (b) Compared to supervised learning (SL), CLIP's performance (measured by accuracy) is less biased by data frequency, and the classifier is notably
Severe data imbalance naturally exists among web-scale vision-language datasets.
Generative Modeling by Estimating Gradients of the Data Distribution
Generative models have many applications in machine learning. To list a few, they have been usedtogenerate high-fidelity images [26,6],synthesize realistic speech andmusic fragments [58], improve the performance of semi-supervised learning [28, 10], detect adversarial examples and other anomalous data [54], imitation learning [22], and explore promising states in reinforcement learning [41].
N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
Shengchao Liu, Mehmet F. Demirel, Yingyu Liang
Neural Information Processing Systems http://nips.cc/
No-regret Online Learning over Riemannian Manifolds
We establish upper bounds on the regrets of the problem with respect to time horizon, manifold curvature, and manifold dimension.
OntheSampleComplexityofPrivatelyLearning Axis-Aligned Rectangles
We say that thisprocedure preservesdifferential privacyifno individual'sdata has asignificant effect on the distribution of the outcome of the procedure.
TowardsSample-efficientOverparameterized Meta-learning
An overarching goal in machine learning is to build ageneralizable model with fewsamples.
A.1 EquivalencebetweenPreConvSAandvanillaSA OurproposedPreConvSAisformulatedinEquation1. f0i =MLPs fli fl+1
Inspired by the depthwise separable convolution used in MobileNet [1], we extend this separable idea to graph convolution. We only perform MLPs on point features directly to learn thechannelcorrelation, andleverages theanisotropic reduction toaggregatethespatial correlation.