arXiv:2609.27179v1 Announce Type: cross Abstract: We study distribution-free sequential changepoint detection for independent observations with unknown and unrestricted pre- and post-change laws. We...
arXiv:2610. 23131v1 Announce Type: cross Abstract: Conformal test martingales (CTMs) are e-processes for sequentially testing exchangeability via p-values produced by a conformity function $A$.
arXiv:2602. 13848v2 Announce Type: replace Abstract: We propose a sequential test for detecting arbitrary distribution shifts that allows conformal test martingales (CTMs) to work under a fixed, reference-conditional setting.
arXiv:2606. 01256v1 Announce Type: cross Abstract: This paper introduces a distribution-free framework for constructing post-detection confidence sets for changepoints after stopping a sequential change detection procedure.
arXiv:2606. 14488v1 Announce Type: cross Abstract: Recent finite-time analyses of nonlinear two-time-scale stochastic approximation show that under contractive assumptions the slow iterate $Y_k$ with stepsizes $\beta_k=\Theta(k^{-1})$ and $\alpha_k=\Theta(k^{-a})$, $a\in(1/2,1)$, generally satisfies a mean-square rate of order $k^{-a}$; decoupled $k^{-1}$ rates require strong local linearity.
arXiv:2606. 20859v2 Announce Type: replace-cross Abstract: A fundamental assumption in statistics and machine learning is that ``the future looks like the past,'' formalized as exchangeability: the joint data distribution is order-invariant.
arXiv:2609. 08234v1 Announce Type: cross Abstract: Suppose we are given an ordered sequence of independent data whose distribution changes $K$ times at unknown locations, for some unknown $K \geq 0$.
The paper extends the e‑closure principle for multiple testing to general state and action spaces and to arbitrarily indexed risk families. It introduces a recertification method that reallocates unused risk budget, enlarging certifying e‑values while preserving validity and yielding less conservative decisions. Applications include improved conformal risk control and enhanced false discovery rate procedures, with empirical gains shown on CIFAR‑100 and simulations.
The paper investigates online fair allocation of sequential items to agents with heterogeneous preferences, aiming to maximize generalized-mean welfare. In an i.i.d. arrival setting, a pure greedy algorithm achieves near-optimal “~O(1/T)” average regret without needing distributional knowledge. For nonstationary arrivals, the authors show that a single historical sample per distribution suffices to recover the same regret rate, using re-solving algorithms that remain robust to distribution shifts.
arXiv:2602. 21479v3 Announce Type: replace-cross Abstract: Across many risk-sensitive areas, it is critical to continuously audit machine learning systems as we receive more data to quickly determine if they are performing as designed.
arXiv:2606. 06785v1 Announce Type: cross Abstract: We study finite-sample change detection for one-dimensional noisy dynamical systems using partition-based empirical approximations of stationary behaviour.
arXiv:2610. 13901v1 Announce Type: cross Abstract: We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process.