The paper introduces a leave‑a‑window‑out estimator for next‑token functionals, such as the surprise probability and test error, in sequences of random variables. By deleting a window of length τ after each index, the estimator generalizes leave‑one‑out and achieves parametric error decay for stationary β‑mixing processes that admit a Marton coupling. The authors provide both upper bounds and a minimax lower bound for the surprise probability, and demonstrate through simulations that their method outperforms traditional baselines on Markov, moving‑average, and autoregressive processes.
By Milind Nakul, Vidya Muthukumar, Ashwin Pananjady
The paper introduces a unified framework for estimating the probability that an unknown distribution assigns to a data‑dependent event defined by a sample and a known mapping. It analyzes two classical estimators—the empirical plug‑in estimator and the leave‑one‑out (Good–Turing) estimator—showing how their errors relate to generalization gaps and stability under sample deletion. The framework is applied to error estimation for predictors that combine a base classifier with memorized exceptions, leading to new bounds based on VC dimension and mutual information for adaptive missing mass estimation.
By Vitaly Feldman, Satyen Kale, Vinod Raman, Kunal Talwar, Ambuj Tewari
arXiv:2608. 25551v1 Announce Type: new Abstract: Stochastic gradient descent (SGD) is typically analyzed at a deterministic horizon chosen before the algorithm is run, even though practical stopping decisions are made adaptively by inspecting the evolving trajectory.
By Liviu Aolaritei, Lucas L\'evy, Francis Bach, Michael I. Jordan
arXiv:2608. 07224v1 Announce Type: new Abstract: Motivated by LLMs, which generate outputs by iteratively sampling from next-token distributions, we introduce a PAC-learning model for binary stochastic autoregressive learning.
By Ilan Doron-Arad, Idan Mehalel, Elchanan Mossel
The paper develops a nonparametric empirical Bayes approach for estimating sums of functions of observable and unobservable variables in Poisson mixture models, using regular and coarsened minimum‑distance estimation of the mixing distribution. It proves large‑sample guarantees that the plug‑in estimates converge to the oracle Bayes estimate, achieving nearly parametric rates when the mixing distribution has finite support. Finite‑sample analyses are provided for two specific sums—total intensity below a threshold and the number of units exceeding latent intensity—along with minimax regret bounds and conditions for bounded regret.
By Stefano Favaro, Sandra Fortini, Soham Jana
arXiv:2610.20007v1 Announce Type: cross
Abstract: We study the minimax estimation of the pseudo-spectral gap $\gamma_{ps}$ of a Markov chain from the observation of a single trajectory. Extending ear...
By Vahe Karagulyan, Miko{\l}aj Kasprzak, Pierre Alquier
arXiv:2608. 14408v1 Announce Type: cross Abstract: We study online statistical inference for functionals of the return distribution under a fixed policy.
By Yang Peng, Liangyu Zhang
The paper investigates how Chain-of-Thought (CoT) reasoning enables Large Language Models to generalize to out-of-distribution (OOD) tasks by composing reusable in-distribution (ID) atomic steps. It provides a theoretical framework showing that OOD risk depends on the sum of ID sub-task risks, scaled by a factor independent of the number of reasoning steps, and that the estimation error grows sub-linearly with the number of steps. Experiments on Atom-Task and GSM8K datasets confirm that CoT supports short-to-long and compositional generalization, and that explicit state tracking is essential.
By Nuo-Jing Liang, Xiao-Tong Yuan, Pan Zhou
The paper extends the idea that contexts are cheap for linear bandits from i.i.d. settings to Markovian context processes. By assuming uniform geometric ergodicity, the authors construct a stationary surrogate action set and use a delayed‑update scheme to mitigate bias from nonstationary conditional context distributions. They provide a phased algorithm for unknown stationary distributions and achieve high‑probability regret bounds comparable to standard linear bandit oracles in fast‑mixing regimes, with empirical validation showing gains over LinUCB.
By Kaan Buyukkalayci, Osama Hanna, Christina Fragouli
arXiv:2602. 05657v2 Announce Type: replace Abstract: The study of tail behaviour of SGD-induced processes has been attracting a lot of interest, due to offering strong guarantees with respect to individual runs of an algorithm.
By Aleksandar Armacki, Dragana Bajovi\'c, Du\v{s}an Jakoveti\'c, Soummya Kar, Ali H. Sayed
arXiv:2603. 06957v2 Announce Type: replace-cross Abstract: We study post-training linear autoregressive models with outcome and process rewards.
By Alireza Mousavi-Hosseini, Murat A. Erdogdu
This paper studies the statistical properties of Stochastic Gradient Descent (SGD) with a constant step size using the framework of iterated random functions. It demonstrates convergence in Euclidean distance via Geometric Moment Contraction, establishes quenched central limit theorems, invariance principles, and α-stable convergence for averaged SGD regardless of initialization, and explores the effect of step sizes through derivative processes. The authors further develop a Richardson-Romberg extrapolation with multiple step sizes, propose a bias-reduced variant, and introduce an online inference method that yields empirical confidence intervals with coverage approaching nominal levels as sample size increases.
By Jiaqi Li, Zhipeng Lou, Stefan Richter, Wei Biao Wu