Statistical Learning
Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data
Kai Helli, David Schnurr, Noah Hollmann, Samuel Müller, Frank Hutter
Until now, no tabular method has consistently outperformed classical supervised learning, which ignores these shifts.
Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
Transformers learn to approximate second-order optimization methods for ICL.
Stopping Bayesian Optimization with Probabilistic Regret Bounds
Monte Carlo stopping rules in a manner that is both sample efficient and robust to estimation error.
Statistical Multicriteria Benchmarking via the GSD-Front
For (3), we relax our proposed test using techniques from robust statistics and imprecise probabilities.
Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors
Recent advancements in solving Bayesian inverse problems have spotlighted de-noising diffusion models (DDMs) as effective priors. Although these have great potential, DDM priors yield complex posterior distributions that are challenging to sample.
Evaluating language models as risk scores
Current question-answering benchmarks predominantly focus on accuracy in realizable prediction tasks.