Statistical Learning
Errors-in-variables Fréchet Regression with Low-rank Covariate Approximation
Fréchet regression has emerged as a promising approach for regression analysis involving non-Euclidean response variables.
Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization
Previous works have implicitly studied that FL suffers from the "client-drift" problem, which is caused by the inconsistent optimum across local clients.
Max-Sliced Mutual Information
This work proposes a middle ground in the form of a scalable information-theoretic generalization of CCA, termed max-sliced mutual information (mSMI).
Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model
It is crucial to quantify the uncertainty of these dynamics models when using them for planning.
Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation Adam Fisch, Joshua Maynez, R. Alex Hofer Bhuwan Dhingra Amir Globerson William W. Cohen
Evaluating machine learning models requires evaluation data.
Operator World Models for Reinforcement Learning
However, it is not directly applicable to Reinforcement Learning (RL) due to the inaccessibility of explicit action-value functions.
GO4Align: Group Optimization for Multi-Task Alignment
Multi-task learning is a promising paradigm for handling several tasks simultaneously using a unified architecture.