Tight Generalization Bounds for Noiseless Inverse Optimization
arXiv:2605.08866v2 Announce Type: replace Abstract: Inverse optimization (IO) seeks to infer the parameters of a decision-maker's objective from observed contex…
EnglisharXiv stat.ML
最新资讯
言栖资讯收录 190394 篇 AI、开发与建站文章，按发布时间排序，支持搜索与按语言筛选。
Online Conformal Prediction via Universal Portfolio Algorithms
arXiv:2602.03168v2 Announce Type: replace Abstract: Online conformal prediction (OCP) seeks prediction intervals that achieve long-run $1-\alpha$ coverage for a…
EnglisharXiv stat.ML
Variational Estimators for Node Popularity Models
arXiv:2511.17783v2 Announce Type: replace Abstract: Node popularity is recognized as a key factor in modeling real-world networks, capturing heterogeneity in co…
EnglisharXiv stat.ML
On the Rate of Gaussian Approximation for Online Linear Regression Problems
arXiv:2509.14039v2 Announce Type: replace Abstract: In this paper, we consider the problem of Gaussian approximation for the online linear regression task. We d…
EnglisharXiv stat.ML
Spectral and Subspace Dynamics of LoRA in Supervised Fine-Tuning and Reinforcement Learning
arXiv:2611.08414v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) is commonly used in both supervised fine-tuning (SFT) and reinforcement learning (R…
EnglisharXiv stat.ML
Conformal Prediction for Time-Dependent PDEs
arXiv:2611.08409v1 Announce Type: cross Abstract: Uncertainty quantification is crucial in scientific machine learning, where models inform safety-critical task…
EnglisharXiv stat.ML
BUMP: Brief Unexpected Mid-Interpolation Peak
arXiv:2611.08182v1 Announce Type: cross Abstract: We identify an intriguing phenomenon when linearly interpolating between permutation-aligned neural networks: …
EnglisharXiv stat.ML
Doubly-robust causal inference for multi-valued treatment regimes with recurrent neural networks
arXiv:2611.08077v1 Announce Type: cross Abstract: We propose a doubly-robust method to estimate the causal effects of multi-valued treatment regimes on patient …
EnglisharXiv stat.ML
Optimal Learning in Games with Arbitrary Delays: Best-of-Both-Worlds for Self-Play and Adversarial Opponents
arXiv:2611.07773v1 Announce Type: cross Abstract: We study learning in zero-sum games with delayed feedback. We introduce Multi-Anchor Optimistic Online Mirror …
EnglisharXiv stat.ML
Identification and Bounding of Joint Expectation over Potential Outcomes
arXiv:2611.07536v1 Announce Type: cross Abstract: The joint expectation of functions of potential outcomes $(Y_1,Y_0)$ is a fundamental quantity in causal infer…
EnglisharXiv stat.ML
Changepoint localization via nested exchangeability tests: from point estimates to confidence intervals
arXiv:2611.07399v1 Announce Type: cross Abstract: We study distribution-free uncertainty quantification for a changepoint estimate in an offline setting. We obs…
EnglisharXiv stat.ML
Last-Iterate Convergence of Stochastic Gradient Methods for Unbounded Problems
arXiv:2611.07334v1 Announce Type: cross Abstract: Last-iterate convergence guarantees for stochastic gradient methods have attracted significant attention as pr…
EnglisharXiv stat.ML
Neural Realized Measures: Forecast-Supervised Intraday Aggregation for Volatility Forecasting
arXiv:2611.07287v1 Announce Type: cross Abstract: High-frequency volatility forecasting typically separates measurement from prediction: intraday observations a…
EnglisharXiv stat.ML
Satisficing as competitive Bayesian weighting: a minimal model of goal-directed choice under an unattained target
arXiv:2611.07270v1 Announce Type: cross Abstract: Animals and humans often do not maximize; they act relative to goals (aspiration levels) that are frequently n…
EnglisharXiv stat.ML
Double Machine Learning for Panel Data: Identification, Specification, and a Bank Regulation Effect
arXiv:2611.07249v1 Announce Type: cross Abstract: This paper examines robustness and causal interpretation of panel estimates using double/debiased machine lear…
EnglisharXiv stat.ML
Unifying Central Flow, Rod Flow, and the Edge Coupling
arXiv:2611.08358v1 Announce Type: new Abstract: At the edge of stability, the iterates of gradient descent oscillate along the sharp directions of the Hessian. …
EnglisharXiv stat.ML
Series-wise Cross-validation for Global Time Series Forecasting
arXiv:2611.08252v1 Announce Type: new Abstract: We consider the problem of cross-validation (CV) in time series forecasting, with a focus on global forecasting …
EnglisharXiv stat.ML
Patch Attention Wisely: Understanding Patch Length in Attention-Based Forecasting
arXiv:2611.08160v1 Announce Type: new Abstract: Attention-based time series forecasters commonly group consecutive observations into patches. Patch length is kn…
EnglisharXiv stat.ML
Identifying Neural Dynamics Using Nonlinear Interventional State Space Models
arXiv:2611.08113v1 Announce Type: new Abstract: State-space models (SSMs) recover low-dimensional latent dynamics from high-dimensional observations, but latent…
EnglisharXiv stat.ML
Joint Modeling of Conditional Mean and Variability in Multilevel Functional Data: Application to Postprandial Glucose Trajectories in the AEGIS Study
arXiv:2611.07937v1 Announce Type: new Abstract: Functional data analysis provides a framework for studying time-varying associations between covariates and high…
EnglisharXiv stat.ML