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.
LC-PFN predicts learning curve performance more accurately and faster than MCMC.
problem Bayesian extrapolation of learning curves is computationally expensive and overly restrictive.
method Prior-Data Fitted Neural Networks (PFNs) for approximate Bayesian inference.
result LC-PFN outperforms MCMC in accuracy and is significantly faster.
PFNs pre-train models on simulated data to predict class probabilities.
problem Training machine learning models on large datasets.
method Pre-train a fixed model on small simulated datasets and use it to infer class probabilities in-context.
result PFNs achieve state-of-the-art performance and improve with larger inference data.
Transformers can approximate Bayesian inference efficiently.
problem Bayesian methods struggle with deep learning due to prior knowledge and uncertainty capture.
method Prior-Data Fitted Networks (PFNs) approximate posteriors using in-context learning.
result PFNs achieve near-perfect mimicry of Gaussian processes and significant speedups.
PFNs4BO uses neural processes for flexible Bayesian Optimization.
problem Efficient surrogate modeling for Bayesian Optimization.
method In-context learning of PFNs to approximate posterior predictive distribution.
result PFNs outperform traditional GP, BNN in BO tasks.
CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching
problem Inference of tabular foundation models with large training datasets
method CRUMB (Clustered Retrieval Using Minimised-MMD Batching)
result CRUMB outperforms state-of-the-art context selection strategies on the TabArena benchmark
LaT-PFN model predicts time series with zero-shot capability.
problem Zero-shot time series forecasting.
method In-context latent space learning with JEPA and PFN integration.
result Superior zero-shot predictions compared to baselines.
Proposes a method to quantify uncertainty in PFNs.
problem Lack of uncertainty quantification in PFNs.
method Martingale posteriors for efficient, tuning-free sampling.
result Proves convergence of proposed sampling procedure.
Decoupled PFNs improve sequential decision-making by separating epistemic and aleatoric uncertainties.
problem Sequential decision-making requires distinguishing between epistemic uncertainty about latent signals and irreducible aleatoric observation noise.
method Developed a decoupled PFN architecture that uses query-level labels to train separate heads for latent signal and aleatoric noise.
result Empirically, decoupled PFNs mitigate the failure mode of total-variance exploration in noisy and heteroscedastic settings.
This paper improves model fusion by training-time neuron alignment, reducing barriers in multi-model fusion.
problem Diverse neuron permutations across different settings hinder model fusion performances.
method Training-time neuron alignment using fixed neuron anchors to reduce training-time permutations.
result Training-time neuron alignment improves fusion of pretrained models and federated learning performances.
New method improves causal structure discovery with Prior-Fitted Networks.
problem Errors in likelihood estimation limit proper causal structure discovery.
method Amortized causal discovery with Prior-Fitted Networks.
result Significant gains in structure recovery compared to baselines.
Transformers can approximate posterior predictive distributions through in-context learning.
problem Bayesian prediction tasks, especially beyond point predictions.
method Gradient descent algorithm targeting posterior predictive mean and variance, followed by nonlinear mappings.
result Transformers can implement algorithms to approximate posterior predictive distributions.
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 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.
CausalPFN automates causal effect estimation from observational data.
problem Manual selection of causal effect estimators is time-consuming and requires domain expertise.
method CausalPFN is a transformer that learns to infer causal effects from raw observations without task-specific adjustments.
result CausalPFN achieves superior performance on various benchmarks and real-world tasks.
Method constructs finance LLMs without instruction data using pretraining and model merging.
problem Developing domain-specific LLMs for finance is resource-intensive.
method Continual pretraining on financial data + model merging of instruction-tuned and domain-specific pretrained vectors.
result Successfully constructs instruction-tuned LLMs for finance without additional instruction data.
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.
Temporal Causal Prior-Data Fitted Networks (TCPFN) for industrial time series causal discovery
problem Estimating causal effects in industrial time series
method Temporal Causal Prior-Data Fitted Networks
result Zero-shot causal discovery with explicit reliability signals