linear regression
Linear regression is a statistical method for modeling the relationship between a dependent variable and one or more independent variables by fitting a linear equation to observed data, widely used for predictive modeling in various domains.
- Are Greedy Task Orderings Better Than Random in Continual Linear Regression?
- Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts
- Data-Adaptive Exposure Thresholds under Network Interference
- Improved Scaling Laws in Linear Regression via Data Reuse
- Mixed-Sample SGD: an End-to-end Analysis of Supervised Transfer Learning
- Optimal Rates in Continual Linear Regression via Increasing Regularization
- Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
- Robust Estimation Under Heterogeneous Corruption Rates
- The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches
- Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression