Accelerated linearized Laplace approximation for Bayesian deep learning
Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of
pretrained deep neural networks to Bayesian neural networks. The generalized Gauss …
pretrained deep neural networks to Bayesian neural networks. The generalized Gauss …
Learning neural eigenfunctions for unsupervised semantic segmentation
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 …
great significance. Spectral clustering is a theoretically grounded solution to it where the …
Uni-fusion: Universal continuous mapping
We present Uni-Fusion, a universal continuous mapping framework for surfaces, surface
properties (color, infrared, etc.) and more (latent features in contrastive language-image …
properties (color, infrared, etc.) and more (latent features in contrastive language-image …
Improved operator learning by orthogonal attention
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 …
received extensive attention in the field of scientific machine learning. Among them, attention …
Contrastive learning can find an optimal basis for approximately view-invariant functions
DD Johnson, A El Hanchi… - The Eleventh International …, 2022 - openreview.net
Contrastive learning is a powerful framework for learning self-supervised representations
that generalize well to downstream supervised tasks. We show that multiple existing …
that generalize well to downstream supervised tasks. We show that multiple existing …
Representations and exploration for deep reinforcement learning using singular value decomposition
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 …
deep reinforcement learning agent. In this work, we provide a singular value decomposition …
A novel stochastic gradient descent algorithm for learning principal subspaces
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 …
number of rows and columns. In several applications like neuroscience, image compression …
Incorporating prior knowledge into neural networks through an implicit composite kernel
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 …
many known properties, such as spatial smoothness or seasonality, are straightforward to …
Contrastive Learning as Kernel Approximation
KC Tsiolis - arXiv preprint arXiv:2309.02651, 2023 - arxiv.org
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 …
the data. While raw data in many application domains is easily obtainable on the Internet …
Spectral representation learning for conditional moment models
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 …
conditional moment models, which characterize the target function through a collection of …