Search Results for author:
Found 62 papers, 23 papers with code
Towards Foundation Models for Critical Care Time Series
This work aims to establish a foundation for training large-scale multi-variate time series models on critical care data and to provide a benchmark for machine learning models in transfer learning across hospitals to study and address distribution shift challenges.
Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanisms
Single-source domain generalization (SDG) aims to learn a model from a single source domain that can generalize well on unseen target domains.
Uncertainty-Penalized Direct Preference Optimization
Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous.
Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information
Knowing which features of a multivariate time series to measure and when is a key task in medicine, wearables, and robotics.
Preference Elicitation for Offline Reinforcement Learning
Drawing on insights from both the offline RL and the preference-based RL literature, our algorithm employs a pessimistic approach for out-of-distribution data, and an optimistic approach for acquiring informative preferences about the optimal policy.
Multi-Modal Contrastive Learning for Online Clinical Time-Series Applications
Electronic Health Record (EHR) datasets from Intensive Care Units (ICU) contain a diverse set of data modalities.
Dynamic Survival Analysis for Early Event Prediction
This study advances Early Event Prediction (EEP) in healthcare through Dynamic Survival Analysis (DSA), offering a novel approach by integrating risk localization into alarm policies to enhance clinical event metrics.
Learning Genomic Sequence Representations using Graph Neural Networks over De Bruijn Graphs
The rapid expansion of genomic sequence data calls for new methods to achieve robust sequence representations.
On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series
Recent findings in deep learning for tabular data are now surpassing these classical methods by better handling the severe heterogeneity of data input features.
Knowledge Graph Representations to enhance Intensive Care Time-Series Predictions
Intensive Care Units (ICU) require comprehensive patient data integration for enhanced clinical outcome predictions, crucial for assessing patient conditions.
Language Model Training Paradigms for Clinical Feature Embeddings
In research areas with scarce data, representation learning plays a significant role.
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion
We answer this question in the affirmative by giving a particular construction of an Multi-Layer Perceptron (MLP) with linear activations and batch-normalization that provably has bounded gradients at any depth.
Multi-modal Graph Learning over UMLS Knowledge Graphs
The results demonstrate the significance of multi-modal medical concept representations based on prior medical knowledge.
Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels
Recent works show that Bayesian model selection with Laplace approximations can allow to optimize such hyperparameters just like standard neural network parameters using gradients and on the training data.
Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding
A prominent challenge of offline reinforcement learning (RL) is the issue of hidden confounding: unobserved variables may influence both the actions taken by the agent and the observed outcomes.
Improving Neural Additive Models with Bayesian Principles
Neural additive models (NAMs) enhance the transparency of deep neural networks by handling input features in separate additive sub-networks.
On the Importance of Clinical Notes in Multi-modal Learning for EHR Data
Understanding deep learning model behavior is critical to accepting machine learning-based decision support systems in the medical community.
Temporal Label Smoothing for Early Event Prediction
TLS reduces the number of missed events by up to a factor of two over previously used approaches in early event prediction.
Ranked #1 on
Respiratory Failure
on HiRID
Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization
We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms.
Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations
We develop a convenient gradient-based method for selecting the data augmentation without validation data during training of a deep neural network.
HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Data
The recent success of machine learning methods applied to time series collected from Intensive Care Units (ICU) exposes the lack of standardized machine learning benchmarks for developing and comparing such methods.
Ranked #1 on
Remaining Length of Stay
on HiRID
Neighborhood Contrastive Learning Applied to Online Patient Monitoring
Intensive care units (ICU) are increasingly looking towards machine learning for methods to provide online monitoring of critically ill patients.
Boosting Variational Inference With Locally Adaptive Step-Sizes
Variational Inference makes a trade-off between the capacity of the variational family and the tractability of finding an approximate posterior distribution.
Early prediction of respiratory failure in the intensive care unit
The development of respiratory failure is common among patients in intensive care units (ICU).
Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning
Marginal-likelihood based model-selection, even though promising, is rarely used in deep learning due to estimation difficulties.
Bayesian Neural Network Priors Revisited
Isotropic Gaussian priors are the de facto standard for modern Bayesian neural network inference.
On Disentanglement in Gaussian Process Variational Autoencoders
While many models have been introduced to learn such disentangled representations, only few attempt to explicitly exploit the structure of sequential data.
WRSE -- a non-parametric weighted-resolution ensemble for predicting individual survival distributions in the ICU
Dynamic assessment of mortality risk in the intensive care unit (ICU) can be used to stratify patients, inform about treatment effectiveness or serve as part of an early-warning system.
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
The idea behind the \emph{unsupervised} learning of \emph{disentangled} representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms.
Scalable Gaussian Process Variational Autoencoders
Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors.
A Commentary on the Unsupervised Learning of Disentangled Representations
The goal of the unsupervised learning of disentangled representations is to separate the independent explanatory factors of variation in the data without access to supervision.
Disentangling Factors of Variations Using Few Labels
Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations.
Weakly-Supervised Disentanglement Without Compromises
Third, we perform a large-scale empirical study and show that such pairs of observations are sufficient to reliably learn disentangled representations on several benchmark data sets.
Deep Amortized Variational Inference for Multivariate Time Series Imputation with Latent Gaussian Process Models
Multivariate time series with missing values are common in areas such as healthcare and finance, and have grown in number and complexity over the years.
DPSOM: Deep Probabilistic Clustering with Self-Organizing Maps
We show that DPSOM achieves superior clustering performance compared to current deep clustering methods on MNIST/Fashion-MNIST, while maintaining the favourable visualization properties of SOMs.
META$^\mathbf{2}$: Memory-efficient taxonomic classification and abundance estimation for metagenomics with deep learning
We therefore aim to develop a more memory-efficient technique for taxonomic classification.
Variational pSOM: Deep Probabilistic Clustering with Self-Organizing Maps
There are very performant deep clustering models on the one hand and interpretable representation learning techniques, often relying on latent topological structures such as self-organizing maps, on the other hand.
Deep Multiple Instance Learning for Taxonomic Classification of Metagenomic read sets
Of particular interest is the determination of the distribution of the taxa of microbes in metagenomic samples.
GP-VAE: Deep Probabilistic Time Series Imputation
Multivariate time series with missing values are common in areas such as healthcare and finance, and have grown in number and complexity over the years.
Disentangling Factors of Variation Using Few Labels
Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations.
Unsupervised Extraction of Phenotypes from Cancer Clinical Notes for Association Studies
To demonstrate the utility of our approach, we perform an association study of clinical features with somatic mutation profiles from 4, 007 cancer patients and their tumors.
Machine learning for early prediction of circulatory failure in the intensive care unit
Intensive care clinicians are presented with large quantities of patient information and measurements from a multitude of monitoring systems.
Meta-Learning Mean Functions for Gaussian Processes
When it comes to meta-learning in Gaussian process models, approaches in this setting have mostly focused on learning the kernel function of the prior, but not on learning its mean function.
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms.
Scalable Gaussian Processes on Discrete Domains
We explore different techniques for selecting inducing points on discrete domains, including greedy selection, determinantal point processes, and simulated annealing.
Boosting Black Box Variational Inference
Finally, we present a stopping criterion drawn from the duality gap in the classic FW analyses and exhaustive experiments to illustrate the usefulness of our theoretical and algorithmic contributions.
SOM-VAE: Interpretable Discrete Representation Learning on Time Series
We evaluate our model in terms of clustering performance and interpretability on static (Fashion-)MNIST data, a time series of linearly interpolated (Fashion-)MNIST images, a chaotic Lorenz attractor system with two macro states, as well as on a challenging real world medical time series application on the eICU data set.
Competitive Training of Mixtures of Independent Deep Generative Models
A common assumption in causal modeling posits that the data is generated by a set of independent mechanisms, and algorithms should aim to recover this structure.
On Matching Pursuit and Coordinate Descent
Exploiting the connection between the two algorithms, we present a unified analysis of both, providing affine invariant sublinear $\mathcal{O}(1/t)$ rates on smooth objectives and linear convergence on strongly convex objectives.
Boosting Variational Inference: an Optimization Perspective
Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one.
Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
We also describe novel evaluation methods for GANs, where we generate a synthetic labelled training dataset, and evaluate on a real test set the performance of a model trained on the synthetic data, and vice-versa.
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees
Greedy optimization methods such as Matching Pursuit (MP) and Frank-Wolfe (FW) algorithms regained popularity in recent years due to their simplicity, effectiveness and theoretical guarantees.
Learning Unitary Operators with Help From u(n)
A major challenge in the training of recurrent neural networks is the so-called vanishing or exploding gradient problem.
Knowledge Transfer with Medical Language Embeddings
Identifying relationships between concepts is a key aspect of scientific knowledge synthesis.
A Generative Model of Words and Relationships from Multiple Sources
We propose a generative model which integrates evidence from diverse data sources, enabling the sharing of semantic information.
Framework for Multi-task Multiple Kernel Learning and Applications in Genome Analysis
We present a general regularization-based framework for Multi-task learning (MTL), in which the similarity between tasks can be learned or refined using $\ell_p$-norm Multiple Kernel learning (MKL).
Bayesian representation learning with oracle constraints
Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy.
Automatic Relevance Determination For Deep Generative Models
A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space.
Probabilistic Clustering of Time-Evolving Distance Data
We present a novel probabilistic clustering model for objects that are represented via pairwise distances and observed at different time points.
GRED: Graph-Regularized 3D Shape Reconstruction from Highly Anisotropic and Noisy Images
Analysis of microscopy images can provide insight into many biological processes.
Hierarchical Multitask Structured Output Learning for Large-scale Sequence Segmentation
We present a novel regularization-based Multitask Learning (MTL) formulation for Structured Output (SO) prediction for the case of hierarchical task relations.
An Empirical Analysis of Domain Adaptation Algorithms for Genomic Sequence Analysis
We study the problem of domain transfer for a supervised classification task in mRNA splicing.
