88 citations · 139 across the 10 of their papers we have counts for
4 papers · 1 filter
Approximate Leave-One-Out for High-Dimensional Non-Differentiable Learning Problems
Shuaiwen Wang, Wenda Zhou, Arian Maleki +2
Consider the following class of learning schemes: \begin{equation} \label{eq:main-problem1} \hat{\boldsymbolβ} := \underset{\boldsymbolβ \in \mathcal{C}}{\arg\min} \;\sum_{j=1}^n \…
Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions
Shuaiwen Wang, Wenda Zhou, Haihao Lu +2
Consider the following class of learning schemes: $$\hat{\boldsymbolβ} := \arg\min_{\boldsymbolβ}\;\sum_{j=1}^n \ell(\boldsymbol{x}_j^\top\boldsymbolβ; y_j) + λR(\boldsymbolβ),\qqu…
Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data
Victor Veitch, Morgane Austern, Wenda Zhou +2
Empirical risk minimization is the main tool for prediction problems, but its extension to relational data remains unsolved. We solve this problem using recent ideas from graph sam…
Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach
Wenda Zhou, Victor Veitch, Morgane Austern +2
Modern neural networks are highly overparameterized, with capacity to substantially overfit to training data. Nevertheless, these networks often generalize well in practice. It has…