arXiv Machine Learning
On Finite-sample Concentration of Median of Incomplete U-Statistics
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 2
On Median of Incomplete U-Statistics
arXiv:2606. 00661v1 Announce Type: cross Abstract: We establish the finite-sample concentration rate for the Median-of-Incomplete-U-Statistics (MIU), an efficient robust estimator for the expectation of symmetric kernels.
arXiv Machine Learning
Oct 15
Hypothesis Selection via Weighted Medians
arXiv:2610.20375v1 Announce Type: cross Abstract: Given $n$ distributions (hypotheses) $\mathcal H=\{H_1,\ldots,H_n\}$ and samples from an unknown target distribution $P$, proper hypothesis selection...
arXiv Machine Learning
Jul 28
Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD
arXiv:2607. 24235v1 Announce Type: cross Abstract: Over the past 20 years, kernel discrepancies have been leveraged as a highly powerful tool for quantifying the disagreement of distributions, with numerous successful applications in two-sample, goodness-of-fit, and independence testing, among others.
arXiv Machine Learning
Oct 12
Approximating Uniform Random Rotations by Two-Stage Structured Hadamard Rotations in High Dimensions
The paper investigates how well two-stage structured Hadamard rotations approximate uniform random rotations in high-dimensional spaces. It establishes nonasymptotic upper bounds of order √{log d/d} for one-dimensional marginals, while showing a persistent Wasserstein-1 discrepancy for the full vector that does not vanish as dimension grows. These results highlight a separation between marginal and joint approximation quality, though they do not directly translate into algorithmic performance guarantees.
arXiv Machine Learning
Jun 15
Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success
arXiv:2606. 14560v1 Announce Type: cross Abstract: Non-Euclidean optimisation methods with matrix-valued updates, such as Muon and Scion, have recently shown strong empirical performance for training Transformer models, yet their theoretical advantages over Euclidean methods remain poorly understood.
arXiv Machine Learning
Oct 7
Sample-Optimal Estimation of the Fr\'echet Inception Distance
The paper investigates the sample complexity of estimating the Fréchet Inception Distance (FID) between high‑dimensional Gaussian distributions when one distribution is known. It establishes tight bias and variance bounds for the empirical plug‑in estimator, shows how higher‑order extrapolation reduces bias, and introduces a new Relative Taylor Debiasing (RTD) algorithm that achieves optimal sample complexity. Experiments on synthetic data and ImageNet confirm the theoretical predictions and demonstrate RTD’s superior accuracy with limited samples.