Search Results for author:
Found 10 papers, 5 papers with code
Random Geometric Graph Alignment with Graph Neural Networks
We characterize the performance of graph neural networks for graph alignment problems in the presence of vertex feature information.
Statistical Guarantees for Link Prediction using Graph Neural Networks
This paper derives statistical guarantees for the performance of Graph Neural Networks (GNNs) in link prediction tasks on graphs generated by a graphon.
Inference on Optimal Dynamic Policies via Softmax Approximation
Estimating optimal dynamic policies from offline data is a fundamental problem in dynamic decision making.
Debiased Machine Learning without Sample-Splitting for Stable Estimators
For instance, we show that the stability properties that we propose are satisfied for ensemble bagged estimators, built via sub-sampling without replacement, a popular technique in machine learning practice.
Data Augmentation in the Underparameterized and Overparameterized Regimes
We provide results that exactly quantify how data augmentation affects the variance and limiting distribution of estimates, and analyze several specific models in detail.
Asymptotics of the Bootstrap via Stability with Applications to Inference with Model Selection
One of the most commonly used methods for forming confidence intervals is the empirical bootstrap, which is especially expedient when the limiting distribution of the estimator is unknown.
Asymptotics of Network Embeddings Learned via Subsampling
We prove, under the assumption that the graph is exchangeable, that the distribution of the learned embedding vectors asymptotically decouples.
Asymptotics of the Empirical Bootstrap Method Beyond Asymptotic Normality
One of the most commonly used methods for forming confidence intervals for statistical inference is the empirical bootstrap, which is especially expedient when the limiting distribution of the estimator is unknown.
Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data
We solve this problem using recent ideas from graph sampling theory to (i) define an empirical risk for relational data and (ii) obtain stochastic gradients for this empirical risk that are automatically unbiased.
Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach
Our main technical result is a generalization bound for compressed networks based on the compressed size.
