Patrick Bloebaum
YOU?
Author Swipe
View article: A Classical View on Benign Overfitting: The Role of Sample Size
A Classical View on Benign Overfitting: The Role of Sample Size Open
Benign overfitting is a phenomenon in machine learning where a model perfectly fits (interpolates) the training data, including noisy examples, yet still generalizes well to unseen data. Understanding this phenomenon has attracted consider…
View article: Benign Overfitting for Regression with Trained Two-Layer ReLU Networks
Benign Overfitting for Regression with Trained Two-Layer ReLU Networks Open
We study the least-square regression problem with a two-layer fully-connected neural network, with ReLU activation function, trained by gradient flow. Our first result is a generalization result, that requires no assumptions on the underly…
View article: Score matching through the roof: linear, nonlinear, and latent variables causal discovery
Score matching through the roof: linear, nonlinear, and latent variables causal discovery Open
Causal discovery from observational data holds great promise, but existing methods rely on strong assumptions about the underlying causal structure, often requiring full observability of all relevant variables. We tackle these challenges b…
View article: Testing Granger Non-Causality in Panels with Cross-Sectional Dependencies
Testing Granger Non-Causality in Panels with Cross-Sectional Dependencies Open
This paper proposes a new approach for testing Granger non-causality on panel data. Instead of aggregating panel member statistics, we aggregate their corresponding p-values and show that the resulting p-value approximately bounds the type…
View article: Why did the distribution change?
Why did the distribution change? Open
We describe a formal approach based on graphical causal models to identify the "root causes" of the change in the probability distribution of variables. After factorizing the joint distribution into conditional distributions of each variab…