599 citations · 1.6k across the 142 of their papers we have counts for
90 papers · 1 filter
Amortizing Sequential Experimental Design in Reasoning LLMs
Anita Kriz, Antonin Berthon, Nicolás Astorga +1
Despite their extensive pretraining knowledge and strong reasoning capabilities, large language models (LLMs) struggle to adaptively gather information in experimental design tasks…
Learning Continuous Patient Trajectories from Electronic Health Records
Silas Ruhrberg Estévez, Kara Liu, Christopher Chiu +4
Electronic health records provide irregular observations of latent patient states that evolve continuously over time. Recent autoregressive models condition on clinical histories t…
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
Julianna Piskorz, Antonin Berthon, Mihaela van der Schaar
On-policy learning has been argued to reduce catastrophic forgetting, produce sparser parameter updates, and improve generalisation. However, existing comparisons between supervise…
: Decision-Targeted Digital Twins
Harry Amad, Mihaela van der Schaar
A digital twin (DT) is a virtual model of a real-world system that can assist decision-making by simulating scenarios induced by different policies. However, typical machine learni…
Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees
Nicolas Huynh, Krzysztof Kacprzyk, Ryan Sheridan +2
The analysis of DNA sequences has become critical in numerous fields, from evolutionary biology to understanding gene regulation and disease mechanisms. While deep neural networks…
Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport
Harry Amad, Mihaela van der Schaar
Neural networks (NNs) often have critical behavioural trade-offs that are set at design time with hyperparameters-such as reward weights in reinforcement learning or quantile targe…
Eliciting Numerical Predictive Distributions of LLMs Without Autoregression
Julianna Piskorz, Katarzyna Kobalczyk, Mihaela van der Schaar
Large Language Models (LLMs) have recently been successfully applied to regression tasks -- such as time series forecasting and tabular prediction -- by leveraging their in-context…
What's the next frontier for Data-centric AI? Data Savvy Agents
Nabeel Seedat, Jiashuo Liu, Mihaela van der Schaar
The recent surge in AI agents that autonomously communicate, collaborate with humans and use diverse tools has unlocked promising opportunities in various real-world settings. Howe…
Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models
Christopher Chiu, Silviu Pitis, Mihaela van der Schaar
Clinical reasoning in medicine is a hypothesis-driven process where physicians refine diagnoses from limited information through targeted history, physical examination, and diagnos…
Overlap-weighted orthogonal meta-learner for treatment effect estimation over time
Konstantin Hess, Dennis Frauen, Mihaela van der Schaar +1
Estimating heterogeneous treatment effects (HTEs) in time-varying settings is particularly challenging, as the probability of observing certain treatment sequences decreases expone…
Deep Hierarchical Learning with Nested Subspace Networks for Large Language Models
Paulius Rauba, Mihaela van der Schaar
Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in res…
Stochastic Encodings for Active Feature Acquisition
Alexander Norcliffe, Changhee Lee, Fergus Imrie +2
Active Feature Acquisition is an instance-wise, sequential decision making problem. The aim is to dynamically select which feature to measure based on current observations, indepen…
Interpretable Reward Modeling with Active Concept Bottlenecks
Sonia Laguna, Katarzyna Kobalczyk, Julia E. Vogt +1
We introduce Concept Bottleneck Reward Models (CB-RM), a reward modeling framework that enables interpretable preference learning through selective concept annotation. Unlike stand…
Not All Explanations for Deep Learning Phenomena Are Equally Valuable
Alan Jeffares, Mihaela van der Schaar
Developing a better understanding of surprising or counterintuitive phenomena has constituted a significant portion of deep learning research in recent years. These include double…
Position: All Current Generative Fidelity and Diversity Metrics are Flawed
Ossi Räisä, Boris van Breugel, Mihaela van der Schaar
Any method's development and practical application is limited by our ability to measure its reliability. The popularity of generative modeling emphasizes the importance of good syn…
Quantifying perturbation impacts for large language models
Paulius Rauba, Qiyao Wei, Mihaela van der Schaar
We consider the problem of quantifying how an input perturbation impacts the outputs of large language models (LLMs), a fundamental task for model reliability and post-hoc interpre…
Unlocking Historical Clinical Trial Data with ALIGN: A Compositional Large Language Model System for Medical Coding
Nabeel Seedat, Caterina Tozzi, Andrea Hita Ardiaca +3
The reuse of historical clinical trial data has significant potential to accelerate medical research and drug development. However, interoperability challenges, particularly with m…
Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner
Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar
Estimating causal quantities from observational data is crucial for understanding the safety and effectiveness of medical treatments. However, to make reliable inferences, medical…
Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond
Alan Jeffares, Alicia Curth, Mihaela van der Schaar
Deep learning sometimes appears to work in unexpected ways. In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate mo…
Matchmaker: Self-Improving Large Language Model Programs for Schema Matching
Nabeel Seedat, Mihaela van der Schaar
Schema matching -- the task of finding matches between attributes across disparate data sources with different tables and hierarchies -- is critical for creating interoperable mach…
Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models
Paulius Rauba, Nabeel Seedat, Max Ruiz Luyten +1
The predominant de facto paradigm of testing ML models relies on either using only held-out data to compute aggregate evaluation metrics or by assessing the performance on differen…
Unveiling the Power of Sparse Neural Networks for Feature Selection
Zahra Atashgahi, Tennison Liu, Mykola Pechenizkiy +3
Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated p…
Discovering Preference Optimization Algorithms with and for Large Language Models
Chris Lu, Samuel Holt, Claudio Fanconi +4
Offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. Typically, preference optimization is approached as…
DAGnosis: Localized Identification of Data Inconsistencies using Structures
Nicolas Huynh, Jeroen Berrevoets, Nabeel Seedat +3
Identification and appropriate handling of inconsistencies in data at deployment time is crucial to reliably use machine learning models. While recent data-centric methods are able…