17 citations · 92 across the 25 of their papers we have counts for
26 papers
Spontaneous Symmetry Breaking in Generative Diffusion Models
Gabriel Raya, Luca Ambrogioni
Generative diffusion models have recently emerged as a leading approach for generating high-dimensional data. In this paper, we show that the dynamics of these models exhibit a spo…
Deterministic training of generative autoencoders using invertible layers
Gianluigi Silvestri, Daan Roos, Luca Ambrogioni
In this work, we provide a deterministic alternative to the stochastic variational training of generative autoencoders. We refer to these new generative autoencoders as AutoEncoder…
Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
Gianluigi Silvestri, Emily Fertig, Dave Moore +1
Normalizing flows have shown great success as general-purpose density estimators. However, many real world applications require the use of domain-specific knowledge, which normaliz…
Knowledge is reward: Learning optimal exploration by predictive reward cashing
Luca Ambrogioni
There is a strong link between the general concept of intelligence and the ability to collect and use information. The theory of Bayes-adaptive exploration offers an attractive opt…
Automatic variational inference with cascading flows
Luca Ambrogioni, Gianluigi Silvestri, Marcel van Gerven
The automation of probabilistic reasoning is one of the primary aims of machine learning. Recently, the confluence of variational inference and deep learning has led to powerful an…
Gradient-adjusted Incremental Target Propagation Provides Effective Credit Assignment in Deep Neural Networks
Sander Dalm, Nasir Ahmad, Luca Ambrogioni +1
Many of the recent advances in the field of artificial intelligence have been fueled by the highly successful backpropagation of error (BP) algorithm, which efficiently solves the…
Explainable 3D Convolutional Neural Networks by Learning Temporal Transformations
Gabriëlle Ras, Luca Ambrogioni, Pim Haselager +2
In this paper we introduce the temporally factorized 3D convolution (3TConv) as an interpretable alternative to the regular 3D convolution (3DConv). In a 3TConv the 3D convolutiona…
GAIT-prop: A biologically plausible learning rule derived from backpropagation of error
Nasir Ahmad, Marcel A. J. van Gerven, Luca Ambrogioni
Traditional backpropagation of error, though a highly successful algorithm for learning in artificial neural network models, includes features which are biologically implausible fo…
Overcoming the Weight Transport Problem via Spike-Timing-Dependent Weight Inference
Nasir Ahmad, Luca Ambrogioni, Marcel A. J. van Gerven
We propose a solution to the weight transport problem, which questions the biological plausibility of the backpropagation algorithm. We derive our method based upon a theoretical a…
Automatic structured variational inference
Luca Ambrogioni, Kate Lin, Emily Fertig +4
Stochastic variational inference offers an attractive option as a default method for differentiable probabilistic programming. However, the performance of the variational approach…
The Indian Chefs Process
Patrick Dallaire, Luca Ambrogioni, Ludovic Trottier +6
This paper introduces the Indian Chefs Process (ICP), a Bayesian nonparametric prior on the joint space of infinite directed acyclic graphs (DAGs) and orders that generalizes India…
Background Hardly Matters: Understanding Personality Attribution in Deep Residual Networks
Gabriëlle Ras, Ron Dotsch, Luca Ambrogioni +2
Perceived personality traits attributed to an individual do not have to correspond to their actual personality traits and may be determined in part by the context in which one enco…
Temporal Factorization of 3D Convolutional Kernels
Gabriëlle Ras, Luca Ambrogioni, Umut Güçlü +1
3D convolutional neural networks are difficult to train because they are parameter-expensive and data-hungry. To solve these problems we propose a simple technique for learning 3D…
Bayesian nonparametric discontinuity design
Max Hinne, David Leeftink, Marcel A. J. van Gerven +1
Quasi-experimental research designs, such as regression discontinuity and interrupted time series, allow for causal inference in the absence of a randomized controlled trial, at th…
k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport
Luca Ambrogioni, Umut Güçlü, Marcel van Gerven
Generative adversarial networks (GANs) are the state of the art in generative modeling. Unfortunately, most GAN methods are susceptible to mode collapse, meaning that they tend to…
Perturbative estimation of stochastic gradients
Luca Ambrogioni, Marcel A. J. van Gerven
In this paper we introduce a family of stochastic gradient estimation techniques based of the perturbative expansion around the mean of the sampling distribution. We characterize t…
Wasserstein variational gradient descent: From semi-discrete optimal transport to ensemble variational inference
Luca Ambrogioni, Umut Guclu, Marcel van Gerven
Particle-based variational inference offers a flexible way of approximating complex posterior distributions with a set of particles. In this paper we introduce a new particle-based…
Wasserstein Variational Inference
Luca Ambrogioni, Umut Güçlü, Yağmur Güçlütürk +3
This paper introduces Wasserstein variational inference, a new form of approximate Bayesian inference based on optimal transport theory. Wasserstein variational inference uses a ne…
Forward Amortized Inference for Likelihood-Free Variational Marginalization
Luca Ambrogioni, Umut Güçlü, Julia Berezutskaya +5
In this paper, we introduce a new form of amortized variational inference by using the forward KL divergence in a joint-contrastive variational loss. The resulting forward amortize…
The Kernel Mixture Network: A Nonparametric Method for Conditional Density Estimation of Continuous Random Variables
Luca Ambrogioni, Umut Güçlü, Marcel A. J. van Gerven +1
This paper introduces the kernel mixture network, a new method for nonparametric estimation of conditional probability densities using neural networks. We model arbitrarily complex…
GP CaKe: Effective brain connectivity with causal kernels
Luca Ambrogioni, Max Hinne, Marcel van Gerven +1
A fundamental goal in network neuroscience is to understand how activity in one region drives activity elsewhere, a process referred to as effective connectivity. Here we propose t…
Integral Transforms from Finite Data: An Application of Gaussian Process Regression to Fourier Analysis
Luca Ambrogioni, Eric Maris
Computing accurate estimates of the Fourier transform of analog signals from discrete data points is important in many fields of science and engineering. The conventional approach…
Estimating Nonlinear Dynamics with the ConvNet Smoother
Luca Ambrogioni, Umut Güçlü, Eric Maris +1
Estimating the state of a dynamical system from a series of noise-corrupted observations is fundamental in many areas of science and engineering. The most well-known method, the Ka…
Complex-valued Gaussian Process Regression for Time Series Analysis
Luca Ambrogioni, Eric Maris
The construction of synthetic complex-valued signals from real-valued observations is an important step in many time series analysis techniques. The most widely used approach is ba…