Search Results for author:
Found 9 papers, 4 papers with code
Deep processing of structured data
We construct a general unified framework for learning representation of structured data, i. e. data which cannot be represented as the fixed-length vectors (e. g. sets, graphs, texts or images of varying sizes).
Set Aggregation Network as a Trainable Pooling Layer
Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data.
Non-linear ICA based on Cramer-Wold metric
Non-linear source separation is a challenging open problem with many applications.
WICA: nonlinear weighted ICA
Independent Component Analysis (ICA) aims to find a coordinate system in which the components of the data are independent.
Analyzing Neural Networks Based on Random Graphs
We perform a massive evaluation of neural networks with architectures corresponding to random graphs of various types.
Neural networks adapting to datasets: learning network size and topology
We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a standard gradient-based training.
On the relationship between disentanglement and multi-task learning
One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks.
Non-Gaussian Gaussian Processes for Few-Shot Regression
This makes the GP posterior locally non-Gaussian, therefore we name our method Non-Gaussian Gaussian Processes (NGGPs).
Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery
In this work, we propose a novel Gradient-based Intervention Targeting method, abbreviated GIT, that 'trusts' the gradient estimator of a gradient-based causal discovery framework to provide signals for the intervention acquisition function.
