arXiv subjects

David Holzmüller

Publications and source records attributed to David Holzmüller.

At least 19 recordsLinked to original sources

arXiv2026

TabICLv2: A better, faster, scalable, and open tabular foundation model

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 learning for tabular data. We introduce TabICLv2, a new state-of-the-art foundation model for regression and classification built on three pillars: (1) a novel synthetic data generation engine designed for high pretraining diversity; (2) various architectural innovations, including a new scalable softmax in attention improving generalization to larger datasets without prohibitive long-sequence pretraining; and (3) optimized pretraining protocols, notably replacing AdamW with the Muon optimizer. On the TabArena and TALENT benchmarks, TabICLv2 without any tuning surpasses the performance of the current state of the art, RealTabPFN-2.5 (hyperparameter-tuned, ensembled, and fine-tuned on real data). With only moderate pretraining compute, TabICLv2 generalizes effectively to million-scale datasets under 50 GB GPU memory while being markedly faster than RealTabPFN-2.5. We provide extensive ablation studies to quantify these contributions and foster open research by releasing code for inference, pretraining, and synthetic data generation at https://github.com/soda-inria/tabicl.

cs.LG↗

arXiv2026

Beyond IID: How General Are Tabular Foundation Models, Really?

Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry. Research communities across disciplines are increasingly evaluating tabular foundation models on diverse datasets and tasks. However, these task- and discipline-specific evaluations remain largely inaccessible to model researchers because benchmark software and evaluation protocols are fragmented. As a result, model researchers rely on standard benchmarks, which are mostly defined for tasks where tabular foundation models already excel. The most challenging scenarios are excluded, limiting meaningful progress in the field by focusing on marginal improvements on IID data rather than on broader, more demanding challenges. To overcome this, we introduce BeyondArena, the first unified holistic benchmark for tabular data that supports diverse task types (IID, temporal, grouped), across sample size and feature dimensionality scales, with diverse feature types (with text, with high cardinality) from a broad range of disciplines. To enable unified benchmarking beyond standard benchmarks, we introduce Data Foundry, a Python framework and metadata schema for curating tabular datasets for predictive machine learning. Our results across 11 models and 142 curated datasets show that existing tabular foundation models excel on tiny- to medium-sized IID data, while traditional tree-based and deep learning models still dominate on non-IID, large, and high-dimensional datasets. BeyondArena guides model research for the most demanding challenges in tabular data, enabling progress towards truly foundational tabular models.

cs.LG↗

arXiv2026

CalArena: A Large-Scale Post-Hoc Calibration Benchmark

Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated. Post-hoc calibration provides a simple and widely used solution, but the large number of proposed methods, combined with small-scale and inconsistent evaluations, makes it difficult to determine which approaches are truly effective in practice. We introduce a large-scale, standardized benchmark for post-hoc calibration, covering nearly 2000 experiments across tabular and computer vision tasks, including binary, multiclass, and large-scale classification settings. Our benchmark aggregates predictions from a diverse set of classical models, modern deep learning architectures, and foundation models, and provides unified, reproducible implementations of dozens of calibration methods within a common evaluation framework. We argue that Post-Hoc Improvement (PHI) in proper scoring rules offers a principled alternative to traditional calibration error estimators for comparing post-hoc methods, capturing both calibration quality and potential degradation to the model's predictive performance. Using this framework, we conduct the most comprehensive empirical study of post-hoc calibration to date. Our results reveal consistent patterns across domains: smooth calibration functions outperform binning-based approaches, dedicated multiclass methods are essential in high-dimensional settings, and generic machine learning models are not competitive without calibration-specific design. To facilitate future research, we release all data, code, and evaluation tools, providing a plug-and-play benchmark for developing and comparing calibration methods.

cs.LG↗

arXiv2026

Conditional Coverage Diagnostics for Conformal Prediction

Evaluating conditional coverage remains one of the most persistent challenges in assessing the reliability of predictive systems. Although conformal methods can give guarantees on marginal coverage, no method can guarantee to produce sets with correct conditional coverage, leaving practitioners without a clear way to interpret local deviations. To overcome sample-inefficiency and overfitting issues of existing metrics, we cast conditional coverage estimation as a classification problem. Conditional coverage is violated if and only if some classifier can achieve lower risk than the target coverage. Through the choice of a (proper) loss function, the resulting risk difference gives a conservative estimate of natural miscoverage measures such as L1 and L2 distance, and can even separate the effects of over- and under-coverage, and non-constant target coverages. We call the resulting family of metrics excess risk of the target coverage (ERT). We show experimentally that the use of modern classifiers provides much higher statistical power than simple classifiers underlying established metrics like CovGap. Additionally, we use our metric to benchmark different conformal prediction methods. Finally, we release an open-source package for ERT as well as previous conditional coverage metrics. Together, these contributions provide a new lens for understanding, diagnosing, and improving the conditional reliability of predictive systems.

stat.ML↗

arXiv2026

STRABLE: Benchmarking Tabular Machine Learning with Strings

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, and these settings have been understudied due to a lack of a solid benchmarking suite. They lead to new research questions: Are dedicated learners needed, with end-to-end modeling of strings and numbers? Or does it suffice to encode strings as numbers, as with a categorical encoding? And if so, do the resulting tables resemble numerical tabular data, calling for the same learners? To enable these studies, we contribute STRABLE, a benchmarking corpus of 108 tables, all real-world learning problems with strings and numbers across diverse application fields. We run the first large-scale empirical study of tabular learning with strings, evaluating 445 pipelines. These pipelines span end-to-end architectures and modular pipelines, where strings are first encoded, then post-processed, and finally passed to a tabular learner. We find that, because most tables in the wild are categorical-dominant, advanced tabular learners paired with simple string embeddings achieve good predictions at low computational cost. On free-text-dominant tables, large LLM encoders become competitive. Their performance also appears sensitive to post-processing, with differences across LLM families. Finally, we show that STRABLE is a good set of tables to study "string tabular" learning as it leads to generalizable pipeline rankings that are close to the oracle rankings. We thus establish STRABLE as a foundation for research on tabular learning with strings, an important yet understudied area.

cs.LG↗

arXiv2026

MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack native support for unstructured modalities such as text and image, and rely on frozen, pretrained embeddings to process them. On established Multimodal Tabular Learning benchmarks, we show that tuning the embeddings to the task improves performance. Existing benchmarks, however, often focus on the mere co-occurrence of modalities; this leads to high variance across datasets and masks the benefits of task-specific tuning. To address this gap, we introduce MulTaBench, a benchmark of 40 datasets, split equally between image-tabular and text-tabular tasks. We focus on predictive tasks where the modalities provide complementary predictive signal, and where generic embeddings lose critical information, necessitating Target-Aware Representations that are aligned with the task. Our experimental results demonstrate that the gains from target-aware representation tuning generalize across both text and image modalities, several tabular learners, encoder scales, and embedding dimensions. MulTaBench constitutes the largest image-tabular benchmarking effort to date, spanning high-impact domains such as healthcare and e-commerce. It is designed to enable the research of novel architectures which incorporate joint modeling and target-aware representations, paving the way for the development of novel Multimodal Tabular Foundation Models.

cs.LG↗

arXiv2026

Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks

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 networks. However, the property of these kernels are poorly understood for activation functions other than powers of the ReLU. Our main contribution is a characterization of the RKHS of these kernels for activation functions whose only non-smoothness is at zero. This extends existing theory to numerous commonly used activation functions such as SELU, ELU, or LeakyReLU. Additionally, we analyze a broad set of special cases such as missing biases, two-layer networks, or polynomial activations. Our results show that a broad class of not infinitely smooth activations generate equivalent RKHSs at different network depths, depending only on the degree of the non-smoothness up to equivalence. On the other hand, the RKHS generated by polynomial activations depends on the network depth. Finally, we derive results for the smoothness of NNGP sample paths, characterizing the smoothness of infinitely wide neural networks at initialization.

stat.ML↗

arXiv2026

Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation

Sampling from Gibbs distributions and computing their log-partition function are fundamental tasks in statistics, machine learning, and statistical physics. While efficient algorithms are known for log-concave densities, the worst-case non-log-concave setting necessarily suffers from the curse of dimensionality. For many numerical problems, the curse of dimensionality can be alleviated when the target function is smooth, allowing the exponent in the rate to improve linearly with the number of available derivatives. Recently, it has been shown that similarly fast convergence rates can be achieved by efficient optimization algorithms. Since optimization can be seen as the low-temperature limit of sampling from Gibbs distributions, we pose the question of whether similarly fast convergence rates can be achieved for non-log-concave sampling. We first study the information-based complexity of the sampling and log-partition estimation problems and show that the optimal rates for sampling and log-partition computation are sometimes equal and sometimes faster than for optimization. We then analyze various polynomial-time sampling algorithms, including an extension of a recent promising optimization approach, and find that they sometimes exhibit interesting behavior but no near-optimal rates. Our results also give further insights into the relation between sampling, log-partition, and optimization problems.

stat.ML↗

arXiv2026

xRFM: Accurate, scalable, and interpretable feature learning models for tabular data

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 explosive changes in the rest of AI, the best practice for these predictive tasks has been relatively unchanged and is still primarily based on variations of Gradient Boosted Decision Trees (GBDTs). Very recently, there has been renewed interest in developing state-of-the-art methods for tabular data based on recent developments in neural networks and feature learning methods. In this work, we introduce xRFM, an algorithm that combines feature learning kernel machines with a tree structure to both adapt to the local structure of the data and scale to essentially unlimited amounts of training data. We show that compared to $31$ other methods, including recently introduced tabular foundation models (TabPFNv2) and GBDTs, xRFM achieves best performance across $100$ regression datasets and is competitive to the best methods across $200$ classification datasets outperforming GBDTs. Additionally, xRFM provides interpretability natively through the Average Gradient Outer Product.

cs.LG↗

arXiv2026

Structured Matrix Scaling for Multi-Class Calibration

Post-hoc recalibration methods are widely used to ensure that classifiers provide faithful probability estimates. We argue that parametric recalibration functions based on logistic regression can be motivated from a simple theoretical setting for both binary and multiclass classification. This insight motivates the use of more expressive calibration methods beyond standard temperature scaling. For multi-class calibration however, a key challenge lies in the increasing number of parameters introduced by more complex models, often coupled with limited calibration data, which can lead to overfitting. Through extensive experiments, we demonstrate that the resulting bias-variance tradeoff can be effectively managed by structured regularization, robust preprocessing and efficient optimization. The resulting methods lead to substantial gains over existing logistic-based calibration techniques. We provide efficient and easy-to-use open-source implementations of our methods, making them an attractive alternative to common temperature, vector, and matrix scaling implementations.

cs.LG↗

arXiv2026

A Variational Estimator for $L_p$ Calibration Errors

Calibration$\unicode{x2014}$the problem of ensuring that predicted probabilities align with observed class frequencies$\unicode{x2014}$is a basic desideratum for reliable prediction with machine learning systems. Calibration error is traditionally assessed via a divergence function, using the expected divergence between predictions and empirical frequencies. Accurately estimating this quantity is challenging, especially in the multiclass setting. Here, we show how to extend a recent variational framework for estimating calibration errors beyond divergences induced induced by proper losses, to cover a broad class of calibration errors induced by $L_p$ divergences. Our method can separate over- and under-confidence and, unlike non-variational approaches, avoids overestimation. We provide extensive experiments and integrate our code in the open-source package probmetrics (https://github.com/dholzmueller/probmetrics) for evaluating calibration errors.

stat.ML↗

arXiv2026

LOGLO-FNO: Efficient Learning of Local and Global Features in Fourier Neural Operators

Modeling high-frequency information is a critical challenge in scientific machine learning. For instance, fully turbulent flow simulations of the Navier-Stokes equations at Reynolds numbers 3500 and above can generate high-frequency signals due to swirling fluid motions caused by eddies and vortices. Faithfully modeling such signals using neural nets depends on the accurate reconstruction of moderate to high frequencies. However, it has been well known that neural nets exhibit spectral or frequency bias towards learning low-frequency components. Meanwhile, Fourier Neural Operators (FNOs) have emerged as a popular class of data-driven models for surrogate modeling and solving PDEs. Although impressive results were achieved on several PDE benchmark problems, FNOs perform poorly in learning non-dominant frequencies characterized by local features. This limitation stems from spectral bias inherent in neural nets and the explicit exclusion of high-frequency modes in FNOs and their variants. Therefore, to mitigate these issues and improve FNO's spectral learning capabilities to represent a broad range of frequency components, we propose two key architectural enhancements: (i) a parallel branch performing local spectral convolution (ii) a high-frequency propagation module. Moreover, we propose a novel frequency-sensitive loss based on radially binned spectral errors. This introduction of a parallel branch for local convolution reduces the trainable parameters by up to 50% while achieving the accuracy of FNO that relies solely on global convolution. Moreover, our findings demonstrate that the proposed model improves stability over longer rollouts. Experiments on six challenging PDEs in fluid mechanics, wave propagation, and biological pattern formation, and the qualitative and spectral analysis of predictions, show the effectiveness of our method over SOTA neural operator families of baselines.

cs.LG↗

arXiv2025

TabArena: A Living Benchmark for Machine Learning on Tabular Data

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 benchmarks are static. Their design is not updated even if flaws are discovered, model versions are updated, or new models are released. To address this, we introduce TabArena, the first continuously maintained living tabular benchmarking system. To launch TabArena, we manually curate a representative collection of datasets and well-implemented models, conduct a large-scale benchmarking study to initialize a public leaderboard, and assemble a team of experienced maintainers. Our results highlight the influence of validation method and ensembling of hyperparameter configurations to benchmark models at their full potential. While gradient-boosted trees are still strong contenders on practical tabular datasets, we observe that deep learning methods have caught up under larger time budgets with ensembling. At the same time, foundation models excel on smaller datasets. Finally, we show that ensembles across models advance the state-of-the-art in tabular machine learning. We observe that some deep learning models are overrepresented in cross-model ensembles due to validation set overfitting, and we encourage model developers to address this issue. We launch TabArena with a public leaderboard, reproducible code, and maintenance protocols to create a living benchmark available at https://tabarena.ai.

cs.LG↗

arXiv2025

Rethinking Early Stopping: Refine, Then Calibrate

Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses, such as cross-entropy, which decompose into two components: calibration error assesses general under/overconfidence, while refinement error measures the ability to distinguish different classes. In this paper, we present a novel variational formulation of the calibration-refinement decomposition that sheds new light on post-hoc calibration, and enables rapid estimation of the different terms. Equipped with this new perspective, we provide theoretical and empirical evidence that calibration and refinement errors are not minimized simultaneously during training. Selecting the best epoch based on validation loss thus leads to a compromise point that is suboptimal for both terms. To address this, we propose minimizing refinement error only during training (Refine,...), before minimizing calibration error post hoc, using standard techniques (...then Calibrate). Our method integrates seamlessly with any classifier and consistently improves performance across diverse classification tasks.

cs.LG↗

arXiv2025

TabICL: A Tabular Foundation Model for In-Context Learning on Large Data

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 training data as context for the test data and predicting in a single forward pass without parameter updates. While TabPFNv2 foundation model excels on tables with up to 10K samples, its alternating column- and row-wise attentions make handling large training sets computationally prohibitive. So, can ICL be effectively scaled and deliver a benefit for larger tables? We introduce TabICL, a tabular foundation model for classification, pretrained on synthetic datasets with up to 60K samples and capable of handling 500K samples on affordable resources. This is enabled by a novel two-stage architecture: a column-then-row attention mechanism to build fixed-dimensional embeddings of rows, followed by a transformer for efficient ICL. Across 200 classification datasets from the TALENT benchmark, TabICL is on par with TabPFNv2 while being systematically faster (up to 10 times), and significantly outperforms all other approaches. On 53 datasets with over 10K samples, TabICL surpasses both TabPFNv2 and CatBoost, demonstrating the potential of ICL for large data. Pretraining code, inference code, and pre-trained models are available at https://github.com/soda-inria/tabicl.

cs.LG↗

arXiv2025

Active Learning for Neural PDE Solvers

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, they often require large amounts of training data that is costly to obtain. Active learning (AL) could help surrogate models reach the same accuracy with smaller training sets by querying classical solvers with more informative initial conditions and PDE parameters. While AL is more common in other domains, it has yet to be studied extensively for neural PDE solvers. To bridge this gap, we introduce AL4PDE, a modular and extensible active learning benchmark. It provides multiple parametric PDEs and state-of-the-art surrogate models for the solver-in-the-loop setting, enabling the evaluation of existing and the development of new AL methods for neural PDE solving. We use the benchmark to evaluate batch active learning algorithms such as uncertainty- and feature-based methods. We show that AL reduces the average error by up to 71% compared to random sampling and significantly reduces worst-case errors. Moreover, AL generates similar datasets across repeated runs, with consistent distributions over the PDE parameters and initial conditions. The acquired datasets are reusable, providing benefits for surrogate models not involved in the data generation.

cs.LG↗

arXiv2025

Better by Default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data

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 with extensive hyperparameter tuning. We address this discrepancy by introducing (a) RealMLP, an improved multilayer perceptron (MLP), and (b) strong meta-tuned default parameters for GBDTs and RealMLP. We tune RealMLP and the default parameters on a meta-train benchmark with 118 datasets and compare them to hyperparameter-optimized versions on a disjoint meta-test benchmark with 90 datasets, as well as the GBDT-friendly benchmark by Grinsztajn et al. (2022). Our benchmark results on medium-to-large tabular datasets (1K--500K samples) show that RealMLP offers a favorable time-accuracy tradeoff compared to other neural baselines and is competitive with GBDTs in terms of benchmark scores. Moreover, a combination of RealMLP and GBDTs with improved default parameters can achieve excellent results without hyperparameter tuning. Finally, we demonstrate that some of RealMLP's improvements can also considerably improve the performance of TabR with default parameters.

cs.LG↗

arXiv2024

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension

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 statistically consistent even though they interpolate noisy training data. While benign overfitting in fixed dimension has been established for some learning methods, current literature suggests that for regression with typical kernel methods and wide neural networks, benign overfitting requires a high-dimensional setting where the dimension grows with the sample size. In this paper, we show that the smoothness of the estimators, and not the dimension, is the key: benign overfitting is possible if and only if the estimator's derivatives are large enough. We generalize existing inconsistency results to non-interpolating models and more kernels to show that benign overfitting with moderate derivatives is impossible in fixed dimension. Conversely, we show that rate-optimal benign overfitting is possible for regression with a sequence of spiky-smooth kernels with large derivatives. Using neural tangent kernels, we translate our results to wide neural networks. We prove that while infinite-width networks do not overfit benignly with the ReLU activation, this can be fixed by adding small high-frequency fluctuations to the activation function. Our experiments verify that such neural networks, while overfitting, can indeed generalize well even on low-dimensional data sets.

stat.ML↗