Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of
pretrained deep neural networks to Bayesian neural networks. The generalized Gauss …

Unsupervised semantic segmentation is a long-standing challenge in computer vision with
great significance. Spectral clustering is a theoretically grounded solution to it where the …

We present Uni-Fusion, a universal continuous mapping framework for surfaces, surface
properties (color, infrared, etc.) and more (latent features in contrastive language-image …

Neural operators, as an efficient surrogate model for learning the solutions of PDEs, have
received extensive attention in the field of scientific machine learning. Among them, attention …

Contrastive learning is a powerful framework for learning self-supervised representations
that generalize well to downstream supervised tasks. We show that multiple existing …

Abstract Representation learning and exploration are among the key challenges for any
deep reinforcement learning agent. In this work, we provide a singular value decomposition …

Many machine learning problems encode their data as a matrix with a possibly very large
number of rows and columns. In several applications like neuroscience, image compression …

It is challenging to guide neural network (NN) learning with prior knowledge. In contrast,
many known properties, such as spatial smoothness or seasonality, are straightforward to …

In standard supervised machine learning, it is necessary to provide a label for every input in
the data. While raw data in many application domains is easily obtainable on the Internet …

Many problems in causal inference and economics can be formulated in the framework of
conditional moment models, which characterize the target function through a collection of …