8 papers
DAIF: A Data-Driven Intermediate Fusion Framework for Multimodal Supervised Learning via Approximate Message Passing
Sagnik Nandy, Samriddha Lahiry, Pragya Sur +1
Multimodal supervised learning seeks to leverage multiple heterogeneous data sources to improve predictive performance. A central challenge is determining the fusion granularity ac…
Multi-layer Cross-attention is Provably Optimal for Multi-modal In-context Learning
Nicholas Barnfield, Subhabrata Sen, Pragya Sur
Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, existing results focus e…
Characterizing Finite-Dimensional Posterior Marginals in High-Dimensional GLMs via Leave-One-Out
Manuel Sáenz, Pragya Sur
We investigate Bayes posterior distributions in high-dimensional generalized linear models (GLMs) under the proportional asymptotics regime, where the number of features and sample…
Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling
Yufan Li, Pragya Sur
We study the fundamental problem of calibrating a linear binary classifier of the form , where the feature vector is Gaussian, is a link function, and $\…
ROTI-GCV: Generalized Cross-Validation for right-ROTationally Invariant Data
Kevin Luo, Yufan Li, Pragya Sur
Two key tasks in high-dimensional regularized regression are tuning the regularization strength for accurate predictions and estimating the out-of-sample risk. It is known that the…
Predictive Inference in Multi-environment Scenarios
John C. Duchi, Suyash Gupta, Kuanhao Jiang +1
We address the challenge of constructing valid confidence intervals and sets in problems of prediction across multiple environments. We investigate two types of coverage suitable f…
Universality in block dependent linear models with applications to nonparametric regression
Samriddha Lahiry, Pragya Sur
Over the past decade, characterizing the exact asymptotic risk of regularized estimators in high-dimensional regression has emerged as a popular line of work. This literature consi…
Spectrum-Aware Debiasing: A Modern Inference Framework with Applications to Principal Components Regression
Yufan Li, Pragya Sur
Debiasing is a fundamental concept in high-dimensional statistics. While degrees-of-freedom adjustment is the state-of-the-art technique in high-dimensional linear regression, it i…