TabPFN-3 scales tabular prediction models to large datasets and improves performance and speed.
problem Scaling tabular prediction models to large datasets with high performance and efficiency.
method Pretrained on synthetic data, introduces test-time compute scaling, and uses row-chunking.
result Significantly outperforms other models on TabArena and diverse datasets.
TabPFN model outperforms previous methods on tabular data.
problem Improving performance on tabular data regression and classification.
method Transformer-based deep learning model for approximate Bayesian inference.
result TabPFN outperforms previous methods on datasets with up to 10,000 samples.
TabPFN models achieve state-of-the-art performance on tabular data tasks.
problem Lack of interpretability in TabPFN models.
method Adaptations of interpretability methods specifically designed for TabPFN, leveraging in-context learning and LOCO.
result Improved interpretability of TabPFN models through efficient computations and scalable data valuation methods.
TabPFN-2.5 boosts tabular AI performance, especially for large datasets.
problem Improving tabular AI models for large datasets and complex feature sets.
method Advanced tabular foundation model with data augmentation and distillation techniques.
result TabPFN-2.5 outperforms tuned tree-based models and AutoGluon 1.4 on benchmark datasets.
TabPFN model shows strong robustness to noisy data.
problem TabPFN tackles robustness to noisy and imperfect tabular data.
method Empirical robustness analysis of TabPFN's attention mechanisms under various perturbations.
result TabPFN maintains high predictive performance and coherent internal behavior under noisy and imperfect data.
TabPFN's internal geometry topology correlates with dataset reliability.
problem Understanding TabPFN's behavior on structurally difficult tabular geometries.
method Using zigzag persistent homology, studying TabPFN's internal representations on synthetic tabular tasks with known topology.
result Topology of TabPFN's internal representation geometry is strongly associated with dataset-level reliability.
TabPFN quickly classifies small tabular data without tuning.
problem Efficiently classifying small tabular datasets.
method Transformer-based model that learns in-context.
result Competitive performance with state-of-the-art methods.
TabMGP uses a martingale posterior with TabPFN to estimate uncertainty in tabular data.
problem Estimating uncertainty in models like TabPFN for scientific estimands θ. method TabMGP is an MGP built on TabPFN, focusing inference on loss function-defined parameters.
result TabMGP produces credible sets with near-nominal coverage and often outperforms baselines.
TabPFN doesn't outperform GLM and XGBoost for motor insurance pricing.
problem Improving insurance pricing models using Tabular Foundation Models (TFMs).
method Pre-training on synthetic datasets and in-context learning for inference.
result TabPFN does not consistently outperform established baselines, has longer inference times, and is sensitive to training set size.
New method for uncertainty analysis in TabPFN, a state-of-the-art tabular transformer.
problem No method for uncertainty decomposition in TabPFN.
method Casted as a Bayesian predictive inference problem, derived variance estimators using predictive CLT.
result Fast to compute credible bands that target epistemic uncertainty and achieve near-nominal frequentist coverage.
Improved tabular models learn better from real-world data.
problem Tabular models perform poorly on real-world datasets when trained only on synthetic data.
method Continued pre-training on a curated set of real-world datasets.
result Real-TabPFN achieves superior predictive accuracy on 29 datasets.
TabPFN learns to approximate functions on tabular data.
problem TabPFN tackles function approximation on tabular data.
method Treated as a black-box function approximator generator, observed behavior on varied datasets.
result Observed behavior that is both brilliant and baffling.
Tabular FMs struggle with reliable uncertainty quantification.
problem Uncertainty quantification in tabular foundation models.
method Compared TabPFN and Gaussian processes (GPs) across various regression tasks.
result GP outperforms TabPFN in data-scarce settings and when kernels are good priors.
Drift-Resilient TabPFN learns to adapt to changing data distributions.
problem Real-world data often shifts over time, degrading model performance.
method In-Context Learning with a Prior-Data Fitted Network, using structural causal models.
result Significant performance improvements across various datasets.
Transformers fine-tuned on synthetic data boost tabular data classification performance.
problem Improving tabular data classification accuracy.
method Fine-tuning ICL-transformers on synthetic datasets with complex decision boundaries.
result Fine-tuned ICL-transformers outperform regular neural networks on real-world datasets.
Transformer model outperforms classical methods in childhood anemia prediction across diverse countries.
problem Generalizing childhood anemia prediction models across different countries and data scarcity.
method Transformer-based tabular foundation model compared to classical supervised methods using DHS data.
result Transformer model achieves lower Brier score and ECE in low-data settings, outperforming classical models.
Study uses deep learning to predict mycotoxin levels in Irish oats.
problem Predicting mycotoxin contamination in Irish oats to improve crop quality and safety.
method Investigated neural networks and transfer learning models for multi-response prediction.
result Transfer learning model TabPFN provided the best performance.
New benchmark predicts cardiometabolic risk from accelerometer data, with varying accuracy.
problem Lack of accurate tabular benchmarks for cardiometabolic risk from accelerometer data.
method Tabular learning methods (ridge regression, XGBoost, TabPFN v2) applied to NHANES data.
result TabPFN v2 achieves best performance, but triglycerides remain largely unpredictable.
Tabular foundation models outperform other methods in conditional density estimation across various datasets.
problem Estimating the full conditional distribution of a response given tabular covariates, especially in settings with heteroscedasticity, multimodality, or asymmetric uncertainty.
method Benchmarked three tabular foundation model variants (TabPFN and TabICL) against six CDE baselines on 39 real-world datasets.
result Tabular foundation models achieve the best CDE loss, log-likelihood, and CRPS across all sample sizes, outperforming other methods.
This paper improves credit scoring models using a novel dataset distillation technique.
problem Limited scalability of pretrained models for tabular credit scoring datasets.
method Integrates class imbalance-aware dataset distillation with pretrained models.
result Improved AUC by 2.5% in financial datasets.
LLMs are vulnerable to task-irrelevant data changes, limiting their use for data fitting.
problem LLMs' sensitivity to task-irrelevant variations in data representation.
method Analysis of LLMs' performance and attention patterns under various data manipulations.
result LLMs are sensitive to task-irrelevant variations, leading to significant prediction errors.
Foundation models leak sensitive data in synthetic tabular data generation, especially LLaMA 3.3 70B.
problem Privacy leakage in synthetic tabular data generation using foundation models.
method Benchmarked three foundation models (GPT-4o-mini, LLaMA 3.3 70B, TabPFN v2) against four baselines on 35 real-world tables.
result Foundation models, especially LLaMA 3.3 70B, have the highest privacy risk in synthetic tabular data generation.
GOTabPFN improves tabular model performance with compact tokenization for HDLSS data.
problem Making tabular models effective for high-dimensional, low-sample size data without retraining.
method Introducing Graph-guided Ordering with Local Refinement (GO-LR) and Neuro-Inspired Subunit Compression (NSC) to create compact meta-features.
result GOTabPFN improves stability and accuracy in tabular benchmarks with compact tokenization.
GAMformer bridges tabular models and interpretability, offering a single-pass approach.
problem Lack of interpretability in tabular foundation models like TabPFN.
method In-context learning for GAM shape functions, training on synthetic data.
result GAMformer performs comparably to other leading GAMs across various classification benchmarks.
Cold-start PV forecasting uses synthetic histories to train time-series foundation models.
problem Cold-start PV forecasting
method Zero-shot pipeline with synthetic histories
result TabPFN-TS achieves the lowest error under Real Feedback strategy
UnmaskingTrees improves tabular data imputation and generation using gradient-boosted decision trees.
problem Traditional methods outperform advanced deep learning techniques on tabular data imputation benchmarks.
method UnmaskingTrees employs gradient-boosted decision trees to incrementally unmask features for imputation and generation.
result UnmaskingTrees outperforms state-of-the-art methods on tabular imputation and generation benchmarks.
The study evaluates forecast risk-adjusted performance using various metrics.
problem Evaluating forecast reliability beyond accuracy.
method Risk-adjusted performance measures (Sharpe, Sortino, Omega ratios) and Edge Ratio.
result Machine learning models often offer attractive risk profiles but not necessarily higher reliability.
Improving in-context learning for latent space Bayesian optimization by adapting pretraining on molecular latent space.
problem Improving in-context learning for latent space Bayesian optimization.
method Adapting pretraining on molecular latent space.
result Achieving strong performance on held-out molecular optimization benchmarks.
TTT improves transformer models for in-context learning.
problem Improving transformer models for efficient in-context learning.
method Gradient-based TTT method for linear transformers, with theoretical and empirical analysis.
result TTT significantly reduces the sample size required for in-context learning.
AutoStan improves Bayesian models via predictive feedback.
problem Improving Bayesian models written in Stan.
method Iterative improvement of Stan models using NLPD and sampler diagnostics feedback.
result AutoStan can autonomously improve diverse Bayesian models across various structures.
Efficient method predicts plausible probability ranges for credal sets.
problem Computational complexity in training credal predictors for complex models.
method Grounded in relative likelihood, decalibration technique.
result Yields credal sets with strong performance across diverse tasks.
PFN-TS uses Thompson sampling with PFNs to improve contextual bandit performance.
problem Improving contextual bandit performance using Thompson sampling with prior-data fitted networks.
method PFN-TS converts PFN posterior predictives into mean-reward samples using a subsampled predictive central limit theorem.
result PFN-TS achieves the best average rank across nonlinear synthetic and OpenML classification-to-bandit benchmarks.
A new framework separates classifier calibration and discrimination.
problem Combining reliability and resolution in probabilistic predictions.
method Manokhin Probability Matrix separates reliability and resolution using Spiegelhalter Z-statistic and AUC-ROC.
result Classifiers are categorized into four archetypes: Eagle, Bull, Sloth, and Mole.
Tabular data analysis shows GBDTs and NNs perform similarly on most datasets.
problem Determining when NNs outperform GBDTs on tabular data.
method Large-scale comparison of 19 algorithms across 176 datasets.
result For many datasets, GBDTs and NNs perform similarly, with hyperparameter tuning often more important than algorithm choice.