
Orbital MCMC
Markov Chain Monte Carlo (MCMC) is a computational approach to fundament...
read it

Natural Graph Networks
Conventional neural message passing algorithms are invariant under permu...
read it

Federated Learning of User Authentication Models
Machine learningbased User Authentication (UA) models have been widely ...
read it

SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
Normalizing flows and variational autoencoders are powerful generative m...
read it

REMIMO: Recurrent and Permutation Equivariant Neural MIMO Detection
In this paper, we present a novel neural network for MIMO symbol detecti...
read it

MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
This paper introduces MDP homomorphic networks for deep reinforcement le...
read it

Involutive MCMC: a Unifying Framework
Markov Chain Monte Carlo (MCMC) is a computational approach to fundament...
read it

Amortized Causal Discovery: Learning to Infer Causal Graphs from TimeSeries Data
Standard causal discovery methods must fit a new model whenever they enc...
read it

SE(3)Transformers: 3D RotoTranslation Equivariant Attention Networks
We introduce the SE(3)Transformer, a variant of the selfattention modu...
read it

The Convolution Exponential and Generalized Sylvester Flows
This paper introduces a new method to build linear flows, by taking the ...
read it

Bayesian Bits: Unifying Quantization and Pruning
We introduce Bayesian Bits, a practical method for joint mixed precision...
read it

A Data and Compute Efficient Design for LimitedResources Deep Learning
Thanks to their improved data efficiency, equivariant neural networks ha...
read it

Guided Variational Autoencoder for Disentanglement Learning
We propose an algorithm, guided variational autoencoder (GuidedVAE), th...
read it

Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs
A common approach to define convolutions on meshes is to interpret them ...
read it

Neural Enhanced Belief Propagation on Factor Graphs
A graphical model is a structured representation of locally dependent ra...
read it

Gradient ℓ_1 Regularization for Quantization Robustness
We analyze the effect of quantizing weights and activations of neural ne...
read it

Estimating Gradients for Discrete Random Variables by Sampling without Replacement
We derive an unbiased estimator for expectations over discrete random va...
read it

Simple and Accurate Uncertainty Quantification from BiasVariance Decomposition
Accurate uncertainty quantification is crucial for many applications whe...
read it

Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks
The success of deep neural networks in many realworld applications is l...
read it

Learning Likelihoods with Conditional Normalizing Flows
Normalizing Flows (NFs) are able to model complicated distributions p(y)...
read it

Invert to Learn to Invert
Iterative learning to infer approaches have become popular solvers for i...
read it

iRIM applied to the fastMRI challenge
We, team AImsterdam, summarize our submission to the fastMRI challenge (...
read it

DPMAC: The Differentially Private Method of Auxiliary Coordinates for Deep Learning
Developing a differentially private deep learning algorithm is challengi...
read it

Relational Generalized FewShot Learning
Transferring learned models to novel tasks is a challenging problem, par...
read it

BatchShaped Channel Gated Networks
We present a method for gating deeplearning architectures on a finegra...
read it

Supervised Uncertainty Quantification for Segmentation with Multiple Annotations
The accurate estimation of predictive uncertainty carries importance in ...
read it

The Functional Neural Process
We present a new family of exchangeable stochastic processes, the Functi...
read it

Differentiable probabilistic models of scientific imaging with the Fourier slice theorem
Scientific imaging techniques such as optical and electron microscopy an...
read it

DataFree Quantization through Weight Equalization and Bias Correction
We introduce a datafree quantization method for deep neural networks th...
read it

An Introduction to Variational Autoencoders
Variational autoencoders provide a principled framework for learning dee...
read it

Combining Generative and Discriminative Models for Hybrid Inference
A graphical model is a structured representation of the data generating ...
read it

Covariance in Physics and Convolutional Neural Networks
In this proceeding we give an overview of the idea of covariance (or equ...
read it

Deep Scalespaces: Equivariance Over Scale
We introduce deep scalespaces (DSS), a generalization of convolutional ...
read it

DIVA: Domain Invariant Variational Autoencoders
We consider the problem of domain generalization, namely, how to learn r...
read it

Integer Discrete Flows and Lossless Compression
Lossless compression methods shorten the expected representation size of...
read it

Stochastic Beams and Where to Find Them: The GumbelTopk Trick for Sampling Sequences Without Replacement
The wellknown GumbelMax trick for sampling from a categorical distribu...
read it

Gauge Equivariant Convolutional Networks and the Icosahedral CNN
The idea of equivariance to symmetry transformations provides one of the...
read it

Combinatorial Bayesian Optimization using Graph Representations
This paper focuses on Bayesian Optimization  typically considered with ...
read it

Emerging Convolutions for Generative Normalizing Flows
Generative flows are attractive because they admit exact likelihood opti...
read it

Adversarial Variational Inference and Learning in Markov Random Fields
Markov random fields (MRFs) find applications in a variety of machine le...
read it

Graph Refinement based Tree Extraction using MeanField Networks and Graph Neural Networks
Graph refinement, or the task of obtaining subgraphs of interest from ov...
read it

The Deep Weight Prior. Modeling a prior distribution for CNNs using generative models
Bayesian inference is known to provide a general framework for incorpora...
read it

Predictive Uncertainty through Quantization
Highrisk domains require reliable confidence estimates from predictive ...
read it

Relaxed Quantization for Discretized Neural Networks
Neural network quantization has become an important research area due to...
read it

Sinkhorn AutoEncoders
Optimal Transport offers an alternative to maximum likelihood for learni...
read it

Probabilistic Binary Neural Networks
Low bitwidth weights and activations are an effective way of combating ...
read it

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
We present a convolutional network that is equivariant to rigid body mot...
read it

Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks
We propose a semantic segmentation model that exploits rotation and refl...
read it

Rotation Equivariant CNNs for Digital Pathology
We propose a new model for digital pathology segmentation, based on the ...
read it

BOCK : Bayesian Optimization with Cylindrical Kernels
A major challenge in Bayesian Optimization is the boundary issue (Swersk...
read it
Max Welling
is this you? claim profile
Vice President Technologies at Qualcomm Technologies Netherlands, Senior Fellow Canadian Institute for Advanced Research, Cofounder and Chief Scientific Advisor Scyfer B.V.,