Search Results for author:
Found 6 papers, 2 papers with code
FoSR: First-order spectral rewiring for addressing oversquashing in GNNs
On the other hand, adding edges to the message-passing graph can lead to increasingly similar node representations and a problem known as oversmoothing.
Oversquashing in GNNs through the lens of information contraction and graph expansion
We compare the spectral expansion properties of our algorithm with that of an existing curvature-based non-local rewiring strategy.
Learning curves for Gaussian process regression with power-law priors and targets
We characterize the power-law asymptotics of learning curves for Gaussian process regression (GPR) under the assumption that the eigenspectrum of the prior and the eigenexpansion coefficients of the target function follow a power law.
Information Complexity and Generalization Bounds
We present a unifying picture of PAC-Bayesian and mutual information-based upper bounds on the generalization error of randomized learning algorithms.
PAC-Bayes and Information Complexity
We point out that a number of well-known PAC-Bayesian-style and information-theoretic generalization bounds for randomized learning algorithms can be derived under a common framework starting from a fundamental information exponential inequality.
The Variational Deficiency Bottleneck
We introduce a bottleneck method for learning data representations based on information deficiency, rather than the more traditional information sufficiency.
