Statistical Learning
Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
Transformers learn to approximate second-order optimization methods for ICL.
Multinomial Logistic Regression: Asymptotic Normality on Null Covariates in High-Dimensions
This paper investigates the asymptotic distribution of the maximum-likelihood estimate (MLE) in multinomial logistic models in the high-dimensional regime where dimension and sample size are of the same order.
Distributed Personalized Empirical Risk Minimization
To mitigate the negative effect of data heterogeneity (non-IIDness), two common approaches are clustering and personalization.
Scale-invariant Optimal Sampling for Rare-events Data with Sparse Models
Rare-events data refer to binary-response data that are highly imbalanced, i.e., the number of zeros
Stopping Bayesian Optimization with Probabilistic Regret Bounds
Monte Carlo stopping rules in a manner that is both sample efficient and robust to estimation error.