Search Results for author:
Found 26 papers, 18 papers with code
Post-hoc Probabilistic Vision-Language Models
Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks.
Streamlining Prediction in Bayesian Deep Learning
The rising interest in Bayesian deep learning (BDL) has led to a plethora of methods for estimating the posterior distribution.
Probabilistic Circuits for Cumulative Distribution Functions
We show that for distributions over binary random variables these representations (PMF and CDF) are essentially equivalent, in the sense that one can be transformed to the other in polynomial time.
On Hardware-efficient Inference in Probabilistic Circuits
Hence, hardware-efficient computation of PCs is highly interesting for edge computing applications.
Flatness Improves Backbone Generalisation in Few-shot Classification
Deployment of deep neural networks in real-world settings typically requires adaptation to new tasks with few examples.
Characteristic Circuits
In many real-world scenarios, it is crucial to be able to reliably and efficiently reason under uncertainty while capturing complex relationships in data.
Subtractive Mixture Models via Squaring: Representation and Learning
Mixture models are traditionally represented and learned by adding several distributions as components.
The Robust Semantic Segmentation UNCV2023 Challenge Results
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023.
Fixing Overconfidence in Dynamic Neural Networks
Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the difficulty of the inputs.
Transport with Support: Data-Conditional Diffusion Bridges
We integrate Bayesian filtering and optimal control into learning the diffusion process, enabling the generation of constrained stochastic processes governed by sparse observations at intermediate stages and terminal constraints.
Uncertainty-guided Source-free Domain Adaptation
Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model.
Disentangling Model Multiplicity in Deep Learning
This observed 'predictive' multiplicity (PM) also implies elusive differences in the internals of the models, their 'representational' multiplicity (RM).
Periodic Activation Functions Induce Stationarity
Neural network models are known to reinforce hidden data biases, making them unreliable and difficult to interpret.
Leveraging Probabilistic Circuits for Nonparametric Multi-Output Regression
Inspired by recent advances in the field of expert-based approximations of Gaussian processes (GPs), we present an expert-based approach to large-scale multi-output regression using single-output GP experts.
Deep Residual Mixture Models
We propose Deep Residual Mixture Models (DRMMs), a novel deep generative model architecture.
Sum-Product-Transform Networks: Exploiting Symmetries using Invertible Transformations
In this work, we propose Sum-Product-Transform Networks (SPTN), an extension of sum-product networks that uses invertible transformations as additional internal nodes.
Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Probabilistic circuits (PCs) are a promising avenue for probabilistic modeling, as they permit a wide range of exact and efficient inference routines.
DynamicPPL: Stan-like Speed for Dynamic Probabilistic Models
Since DynamicPPL is a modular, stand-alone library, any probabilistic programming system written in Julia, such as Turing. jl, can use DynamicPPL to specify models and trace their model parameters.
Graph Tracking in Dynamic Probabilistic Programs via Source Transformations
Many modern machine learning algorithms, such as automatic differentiation (AD) and versions of approximate Bayesian inference, can be understood as a particular case of message passing on some computation graph.
AdvancedHMC.jl: A robust, modular and efficient implementation of advanced HMC algorithms
Stan's Hamilton Monte Carlo (HMC) has demonstrated remarkable sampling robustness and efficiency in a wide range of Bayesian inference problems through carefully crafted adaption schemes to the celebrated No-U-Turn sampler (NUTS) algorithm.
Deep Structured Mixtures of Gaussian Processes
Gaussian Processes (GPs) are powerful non-parametric Bayesian regression models that allow exact posterior inference, but exhibit high computational and memory costs.
Bayesian Learning of Sum-Product Networks
While parameter learning in SPNs is well developed, structure learning leaves something to be desired: Even though there is a plethora of SPN structure learners, most of them are somewhat ad-hoc and based on intuition rather than a clear learning principle.
Optimisation of Overparametrized Sum-Product Networks
It seems to be a pearl of conventional wisdom that parameter learning in deep sum-product networks is surprisingly fast compared to shallow mixture models.
Learning Deep Mixtures of Gaussian Process Experts Using Sum-Product Networks
In this paper, we introduce a natural and expressive way to tackle these problems, by incorporating GPs in sum-product networks (SPNs), a recently proposed tractable probabilistic model allowing exact and efficient inference.
Probabilistic Deep Learning using Random Sum-Product Networks
The need for consistent treatment of uncertainty has recently triggered increased interest in probabilistic deep learning methods.
Safe Semi-Supervised Learning of Sum-Product Networks
In several domains obtaining class annotations is expensive while at the same time unlabelled data are abundant.
