Search Results for author:
Found 51 papers, 20 papers with code
Decoder ensembling for learned latent geometries
Latent space geometry provides a rigorous and empirically valuable framework for interacting with the latent variables of deep generative models.
A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
Optimizing discrete black-box functions is key in several domains, e. g. protein engineering and drug design.
Reparameterization invariance in approximate Bayesian inference
Current approximate posteriors in Bayesian neural networks (BNNs) exhibit a crucial limitation: they fail to maintain invariance under reparameterization, i. e. BNNs assign different posterior densities to different parametrizations of identical functions.
Gradients of Functions of Large Matrices
Tuning scientific and probabilistic machine learning models -- for example, partial differential equations, Gaussian processes, or Bayesian neural networks -- often relies on evaluating functions of matrices whose size grows with the data set or the number of parameters.
A Continuous Relaxation for Discrete Bayesian Optimization
To optimize efficiently over discrete data and with only few available target observations is a challenge in Bayesian optimization.
Improving Adversarial Energy-Based Model via Diffusion Process
Generative models have shown strong generation ability while efficient likelihood estimation is less explored.
Neural Contractive Dynamical Systems
Stability guarantees are crucial when ensuring a fully autonomous robot does not take undesirable or potentially harmful actions.
Learning to Taste: A Multimodal Wine Dataset
We demonstrate that this shared concept embedding space improves upon separate embedding spaces for coarse flavor classification (alcohol percentage, country, grape, price, rating) and aligns with the intricate human perception of flavor.
Variational Autoencoding of Dental Point Clouds
Digital dentistry has made significant advancements, yet numerous challenges remain.
Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification
Image segmentation relies heavily on neural networks which are known to be overconfident, especially when making predictions on out-of-distribution (OOD) images.
Identifying latent distances with Finslerian geometry
Generative models are often stochastic, causing the data space, the Riemannian metric, and the geodesics, to be stochastic as well.
Probabilistic thermal stability prediction through sparsity promoting transformer representation
Pre-trained protein language models have demonstrated significant applicability in different protein engineering task.
Revisiting Active Sets for Gaussian Process Decoders
Decoders built on Gaussian processes (GPs) are enticing due to the marginalisation over the non-linear function space.
Laplacian Autoencoders for Learning Stochastic Representations
In this work, we present a Bayesian autoencoder for unsupervised representation learning, which is trained using a novel variational lower-bound of the autoencoder evidence.
Is an encoder within reach?
The encoder network of an autoencoder is an approximation of the nearest point projection onto the manifold spanned by the decoder.
Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry
Deep generative models can automatically create content of diverse types.
Visualizing Riemannian data with Rie-SNE
Faithful visualizations of data residing on manifolds must take the underlying geometry into account when producing a flat planar view of the data.
Reactive Motion Generation on Learned Riemannian Manifolds
We argue that Riemannian manifolds may be learned via human demonstrations in which geodesics are natural motion skills.
Model-agnostic out-of-distribution detection using combined statistical tests
These techniques, based on classical statistical tests, are model-agnostic in the sense that they can be applied to any differentiable generative model.
Adaptive Cholesky Gaussian Processes
We present a method to approximate Gaussian process regression models for large datasets by considering only a subset of the data.
Benchmarking Generative Latent Variable Models for Speech
Stochastic latent variable models (LVMs) achieve state-of-the-art performance on natural image generation but are still inferior to deterministic models on speech.
Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization
Place recognition and visual localization are particularly challenging in wide baseline configurations.
Robust uncertainty estimates with out-of-distribution pseudo-inputs training
As one cannot train without data, we provide mechanisms for generating pseudo-inputs in informative low-density regions of the input space, and show how to leverage these in a practical Bayesian framework that casts a prior distribution over the model uncertainty.
Bounds all around: training energy-based models with bidirectional bounds
Energy-based models (EBMs) provide an elegant framework for density estimation, but they are notoriously difficult to train.
Towards Generative Latent Variable Models for Speech
While stochastic latent variable models (LVMs) now achieve state-of-the-art performance on natural image generation, they are still inferior to deterministic models on speech.
Pulling back information geometry
Latent space geometry has shown itself to provide a rich and rigorous framework for interacting with the latent variables of deep generative models.
Learning Riemannian Manifolds for Geodesic Motion Skills
For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly.
Density estimation on smooth manifolds with normalizing flows
We present a framework for learning probability distributions on topologically non-trivial manifolds, utilizing normalizing flows.
Hierarchical VAEs Know What They Don't Know
Deep generative models have been demonstrated as state-of-the-art density estimators.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
What is a meaningful representation of protein sequences?
How we choose to represent our data has a fundamental impact on our ability to subsequently extract information from them.
Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval
Uncertainty quantification in image retrieval is crucial for downstream decisions, yet it remains a challenging and largely unexplored problem.
Reparametrization Invariance in non-parametric Causal Discovery
This study investigates one such invariant: the causal relationship between X and Y is invariant to the marginal distributions of X and Y.
Geometrically Enriched Latent Spaces
A common assumption in generative models is that the generator immerses the latent space into a Euclidean ambient space.
Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
We present a probabilistic model where the latent variable respects both the distances and the topology of the modeled data.
Probabilistic Spatial Transformer Networks
Spatial Transformer Networks (STNs) estimate image transformations that can improve downstream tasks by `zooming in' on relevant regions in an image.
Variational Autoencoders with Riemannian Brownian Motion Priors
Variational Autoencoders (VAEs) represent the given data in a low-dimensional latent space, which is generally assumed to be Euclidean.
Expected path length on random manifolds
Manifold learning seeks a low dimensional representation that faithfully captures the essence of data.
Explicit Disentanglement of Appearance and Perspective in Generative Models
Disentangled representation learning finds compact, independent and easy-to-interpret factors of the data.
Reliable training and estimation of variance networks
We propose and investigate new complementary methodologies for estimating predictive variance networks in regression neural networks.
Fast and Robust Shortest Paths on Manifolds Learned from Data
We propose a fast, simple and robust algorithm for computing shortest paths and distances on Riemannian manifolds learned from data.
Geodesic Clustering in Deep Generative Models
Deep generative models are tremendously successful in learning low-dimensional latent representations that well-describe the data.
Only Bayes should learn a manifold (on the estimation of differential geometric structure from data)
We investigate learning of the differential geometric structure of a data manifold embedded in a high-dimensional Euclidean space.
Probabilistic Riemannian submanifold learning with wrapped Gaussian process latent variable models
Latent variable models (LVMs) learn probabilistic models of data manifolds lying in an \emph{ambient} Euclidean space.
Latent Space Oddity: on the Curvature of Deep Generative Models
Deep generative models provide a systematic way to learn nonlinear data distributions, through a set of latent variables and a nonlinear "generator" function that maps latent points into the input space.
Intrinsic Grassmann Averages for Online Linear, Robust and Nonlinear Subspace Learning
In this paper, we present a geometric framework for computing the principal linear subspaces in both situations as well as for the robust PCA case, that amounts to computing the intrinsic average on the space of all subspaces: the Grassmann manifold.
A Locally Adaptive Normal Distribution
The multivariate normal density is a monotonic function of the distance to the mean, and its ellipsoidal shape is due to the underlying Euclidean metric.
Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation
We then learn a class-specific probabilistic generative models of the transformations in a Riemannian submanifold of the Lie group of diffeomorphisms.
Metrics for Probabilistic Geometries
We investigate the geometrical structure of probabilistic generative dimensionality reduction models using the tools of Riemannian geometry.
Geodesic Exponential Kernels: When Curvature and Linearity Conflict
However, we show that for spaces with conditionally negative definite distances the geodesic Laplacian kernel can be generalized while retaining positive definiteness.
Probabilistic Solutions to Differential Equations and their Application to Riemannian Statistics
We study a probabilistic numerical method for the solution of both boundary and initial value problems that returns a joint Gaussian process posterior over the solution.
A Geometric take on Metric Learning
We then show that this structure gives us a principled way to perform dimensionality reduction and regression according to the learned metrics.
