51 citations · 228 across the 23 of their papers we have counts for
29 papers
SurvICL: a Foundation Model for in-context Survival Analysis
Julie Alberge, Linus Bleistein, Judith Abécassis +3
Tabular foundation models (TFMs) now outperform gradient-boosted trees in classification and regression. Yet in survival analysis, which predicts when an event occurs from censored…
TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings
Félix Lefebvre, David Holzmüller, Gioia Blayer +3
Real-world tables are often heterogeneous, combining numerical features with free-form string columns. Table foundation models (TFMs) excel on numerical tables but require strings…
Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization
Gustavo Sutter, Alejandro Comas-Leon, David Holzmüller +4
Black-box optimization problems are ubiquitous across science and engineering, often dealing with expensive objective functions. This objective latency has two consequences during…
CalArena: A Large-Scale Post-Hoc Calibration Benchmark
Eugène Berta, David Holzmüller, Francis Bach +1
Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated. Post-hoc calibration provides a simple and wi…
STRABLE: Benchmarking Tabular Machine Learning with Strings
Gioia Blayer, Myung Jun Kim, Félix Lefebvre +8
Benchmarking tabular learning has revealed the benefit of dedicated architectures, pushing the state of the art. But real-world tables often contain string entries, beyond numbers,…
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
Alan Arazi, Eilam Shapira, Shoham Grunblat +8
Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numeric…
V-ECE: Estimating General Expected Calibration Errors
Eugène Berta, Sacha Braun, David Holzmüller +2
In probabilistic classification, calibration error (CE) measures the average divergence of predicted probabilities from , the true class distribution for…
TabICLv2: A better, faster, scalable, and open tabular foundation model
Jingang Qu, David Holzmüller, Gaël Varoquaux +1
Tabular foundation models, such as TabPFNv2 and TabICL, have recently dethroned gradient-boosted trees at the top of predictive benchmarks, demonstrating the value of in-context le…
Conditional Coverage Diagnostics for Conformal Prediction
Sacha Braun, David Holzmüller, Michael I. Jordan +1
Evaluating conditional coverage remains one of the most persistent challenges in assessing the reliability of predictive systems. Although conformal methods can give guarantees on…
Structured Matrix Scaling for Multi-Class Calibration
Eugène Berta, David Holzmüller, Michael I. Jordan +1
Post-hoc recalibration methods are widely used to ensure that classifiers provide faithful probability estimates. We argue that parametric recalibration functions based on logistic…
xRFM: Accurate, scalable, and interpretable feature learning models for tabular data
Daniel Beaglehole, David Holzmüller, Adityanarayanan Radhakrishnan +1
Inference from tabular data, collections of continuous and categorical variables organized into matrices, is a foundation for modern technology and science. Yet, in contrast to the…
Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
David Holzmüller, Max Schölpple
In recent years, the neural tangent kernel (NTK) and neural network Gaussian process kernel (NNGP) have given theoreticians tractable limiting cases of fully connected neural netwo…
TabArena: A Living Benchmark for Machine Learning on Tabular Data
Nick Erickson, Lennart Purucker, Andrej Tschalzev +4
With the growing popularity of deep learning and foundation models for tabular data, the need for standardized and reliable benchmarks is higher than ever. However, current benchma…
LOGLO-FNO: Efficient Learning of Local and Global Features in Fourier Neural Operators
Marimuthu Kalimuthu, David Holzmüller, Mathias Niepert
Modeling high-frequency information is a critical challenge in scientific machine learning. For instance, fully turbulent flow simulations of the Navier-Stokes equations at Reynold…
TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
Jingang Qu, David Holzmüller, Gaël Varoquaux +1
The long-standing dominance of gradient-boosted decision trees on tabular data is currently challenged by tabular foundation models using In-Context Learning (ICL): setting the tra…
Rethinking Early Stopping: Refine, Then Calibrate
Eugène Berta, David Holzmüller, Michael I. Jordan +1
Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predi…
Active Learning for Neural PDE Solvers
Daniel Musekamp, Marimuthu Kalimuthu, David Holzmüller +2
Solving partial differential equations (PDEs) is a fundamental problem in science and engineering. While neural PDE solvers can be more efficient than established numerical solvers…
Better by Default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data
David Holzmüller, Léo Grinsztajn, Ingo Steinwart
For classification and regression on tabular data, the dominance of gradient-boosted decision trees (GBDTs) has recently been challenged by often much slower deep learning methods…
Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
Viktor Zaverkin, David Holzmüller, Robin Schuldt +1
The accuracy of the training data limits the accuracy of bulk properties from machine-learned potentials. For example, hybrid functionals or wave-function-based quantum chemical me…
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
Viktor Zaverkin, David Holzmüller, Henrik Christiansen +5
Efficiently creating a concise but comprehensive data set for training machine-learned interatomic potentials (MLIPs) is an under-explored problem. Active learning, which uses bias…
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
Moritz Haas, David Holzmüller, Ulrike von Luxburg +1
The success of over-parameterized neural networks trained to near-zero training error has caused great interest in the phenomenon of benign overfitting, where estimators are statis…
Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation
David Holzmüller, Francis Bach
Sampling from Gibbs distributions and computing their log-partition function are fundamental tasks in statistics, machine learning, and statistical physics. While efficient algorit…
Transfer learning for chemically accurate interatomic neural network potentials
Viktor Zaverkin, David Holzmüller, Luca Bonfirraro +1
Developing machine learning-based interatomic potentials from ab-initio electronic structure methods remains a challenging task for computational chemistry and materials science. T…
A Framework and Benchmark for Deep Batch Active Learning for Regression
David Holzmüller, Viktor Zaverkin, Johannes Kästner +1
The acquisition of labels for supervised learning can be expensive. To improve the sample efficiency of neural network regression, we study active learning methods that adaptively…