Statistical Learning
New Bounds for Hyperparameter Tuning of Regression Problems Across Instances
In this work, we investigate an alternative setting for tuning regularization parameters, namely data-driven algorithm design, following the previous line of work by Balcan et al. [
Context-guided Embedding Adaptation for Effective Topic Modeling in Low-Resource Regimes
A case in point occurs in personalized recommendation systems where users' preferences are judged
On the Robustness of Removal-Based Feature Attributions
In recent years, machine learning has shown great promise in a variety of real-world applications.
Smooth, exact rotational symmetrization for deep learning on point clouds
We propose a general symmetrization method that adds rotational equivariance to any given model while preserving all the other requirements.
Faster Differentially Private Convex Optimization via Second-Order Methods
We first develop a private variant of the regularized cubic Newton method of Nesterov and Polyak [NP06], and show that for the class of strongly convex loss functions, our algorithm has quadratic convergence and achieves the optimal excess loss.
Self-Correcting Bayesian Optimization through Bayesian Active Learning
Gaussian processes are the model of choice in Bayesian optimization and active learning.
