How to DP-Fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy

Subjects: “…Computer Sciience…”
Get full text

Bridging Domain Invariance and Diversity: A Fine-Grained Risk Bound for Domain Generalization

Subjects: “…Computer Sciience…”
Get full text

High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks

Subjects: “…Computer Sciience…”
Get full text

Error Analyses of Auto-Regressive Video Diffusion Models

Subjects: “…Computer Sciience…”
Get full text

Near-optimal Delta-convex Estimation of Lipschitz Functions

Subjects: “…Computer Sciience…”
Get full text

The Sample Complexity of Parameter-Free Stochastic Convex Optimization

Subjects: “…Computer Sciience…”
Get full text

End-to-End Deep Learning for Predicting Metric Space-Valued Outputs

Subjects: “…Computer Sciience…”
Get full text

Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspective

Subjects: “…Computer Sciience…”
Get full text

Learning to Play Two-Player Perfect-Information Games without Knowledge

Subjects: “…Computer Sciience…”
Get full text

Doubly Debiased Robust Subsampling for Transfer Learning

Subjects: “…Computer Sciience…”
Get full text

Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy

Subjects: “…Computer Sciience…”
Get full text

Mixing times of data-augmentation Gibbs samplers for high-dimensional probit regression

Subjects: “…Computer Sciience…”
Get full text

Underdamped Langevin MCMC with third order convergence

Subjects: “…Computer Sciience…”
Get full text

Approximation-Free Differentiable Oblique Decision Trees

Subjects: “…Computer Sciience…”
Get full text

Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes

Subjects: “…Computer Sciience…”
Get full text

Adaptive Nonparametric Perturbations of Parametric Models with Generalized Bayes

Subjects: “…Computer Sciience…”
Get full text

Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss

Subjects: “…Computer Sciience…”
Get full text

Gradient Span Algorithms Make Predictable Progress in High Dimension

Subjects: “…Computer Sciience…”
Get full text

py/cuTAGI: An Open-Source Library for Tractable Approximate Gaussian Inference in Bayesian Neural Networks

Subjects: “…Computer Sciience…”
Get full text

Statistical Test for Attention in Transformers for Images and Time Series

Subjects: “…Computer Sciience…”
Get full text