CORTEXA
← Browse
arxivstat.MLcs.LGstat.CO2026-07-04

Sequential Correlations Change In-Context Learning: Effective Context Length and Architectural Mismatch

Mary Letey, Yue M. Lu, Cengiz Pehlevan, Jacob Zavatone-Veth

Modern sequence models have a striking capacity for in-context learning (ICL); they can perform new tasks based only on examples given in the prompt. Understanding how this ability emerges requires theory that captures important properties of natural data. Linear regression has served as a useful sandbox for ICL theory, but existing work has largely focused on prompts with independent examples. In this work, we extend this setting to sequentially correlated data, a basic feature of real sequences. We present a solvable model based on linear attention and test our predictions on realistic transformer architectures. We identify two distinct effects: First, when the query token is independent of the context, within-context correlations induce an effective context length: correlated prompts behave like shorter i.i.d. prompts. Second, when the query is also correlated with its context, test error is reduced, particularly for softmax attention when compared to linear attention. These results suggest that correlated prompts alter not only the effective sample size of in-context learning, but also which attention architectures are best matched to the task.

View free PDFSource page

Related papers

arxivstat.MLcs.LGmath.NAstat.CO2026-07-24

Convergence analysis of a family of Zermelo-type iterations for the Bradley--Terry model

Ruijian Han, Ding Lu, Yiming Xu

Zermelo's algorithm is a classical method for computing the maximum likelihood estimator in the Bradley--Terry (BT) model, but its convergence can be slow in practice. To accelerate computation, Newman introduced a family of Zermelo-type fixed-point iterations parameterized by $α…

View free PDFSource page
arxivstat.MEcs.LGstat.APstat.COstat.ML2026-07-23

Distributional Determinantal Point Process for Repulsive Clustering of Distributions

Khai Nguyen, Yang Ni, Elizabeth Juarez-Colunga, Peter Mueller

We introduce the distributional determinantal point process (dDPP) as a novel repulsive point process whose atoms are probability distributions rather than points in a real space. The dDPP is constructed via an L-ensemble with a sliced Wasserstein (SW) kernel between distribution…

View free PDFSource page
arxivstat.MEcs.LGstat.ML2026-07-23

Longitudinal Random Forests for Sparse and Irregular Response Trajectories

Yangsheng Wang, Xiaotian Dai, Haoda Fu, Guifang Fu

Longitudinal studies often collect data at sparse, irregular, and unequally spaced time points. Such heterogeneity is often driven by subject-specific covariates, yet existing methods have been restricted to a scalar endpoint value, completely neglecting the underlying response t…

View free PDFSource page
arxivstat.MLcs.LG2026-07-23

Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting

Ferdinand Bhavsar, Lionel Benoit, Maxime Savatier, Edith Gabriel

The modeling of hydrometeorological time series with limited observations is a key challenge in the monitoring of hydro-systems and water resources, as well as for flood or drought risk assessment. Due to the high variability of the underlying processes and the sparsity of availa…

View free PDFSource page
arxivstat.MLcs.LGstat.AP2026-07-31

Analytical and Bootstrap Confidence Intervals of Double Machine Learning: Simulation studies and an application to rural-urban difference in obesity prevalence

Haozheng Xu, Siyuan Ma, Qingyan Xiang

Double Machine Learning (DML) is a popular approach for treatment effect estimation in various settings, which allows a wide range of flexible machine learning methods to be used for nuisance parameter estimation while preserving valid inference. In practice, however, applied res…

View free PDFSource page
arxivcs.LGcs.ITeess.SPstat.ML2026-07-23

Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking

Ahmad Halimi Razlighi, Maximilian H. V. Tillmann, Edgar Beck, Bho Matthiesen, Armin Dekorsy

Cooperative multi-task semantic communication (CMT-SemCom) improves task execution performance by leveraging shared representations. However, as we demonstrated in [1], cooperative multi-tasking can be either constructive or destructive, depending on the semantic relationships am…

View free PDFSource page