Generalization Bounds
131 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Generalization Bounds
Latest papers
Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing
guoji-fu/dignn
•
•
We show how implicit GNN layers can be viewed as the fixed-point equation of a Dirichlet energy minimization problem and give conditions under which it may suffer from over-smoothing during training (OST) and inference (OSI).
Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
dlr-rm/bpnn
•
•
In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks.
How Does Information Bottleneck Help Deep Learning?
xu-ji/information-bottleneck
•
•
In this paper, we provide the first rigorous learning theory for justifying the benefit of information bottleneck in deep learning by mathematically relating information bottleneck to generalization errors.
Double-Weighting for Covariate Shift Adaptation
Supervised learning is often affected by a covariate shift in which the marginal distributions of instances (covariates $x$) of training and testing samples $\mathrm{p}_\text{tr}(x)$ and $\mathrm{p}_\text{te}(x)$ are different but the label conditionals coincide.
Towards Understanding Generalization of Macro-AUC in Multi-label Learning
We theoretically identify a critical factor of the dataset affecting the generalization bounds: \emph{the label-wise class imbalance}.
The Ideal Continual Learner: An Agent That Never Forgets
xialeiliu/Awesome-Incremental-Learning
•
•
We show that ICL unifies multiple well-established continual learning methods and gives new theoretical insights into the strengths and weaknesses of these methods.
AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs
AdapterGNN preserves the knowledge of the large pre-trained model and leverages highly expressive adapters for GNNs, which can adapt to downstream tasks effectively with only a few parameters, while also improving the model's generalization ability.
Energy-guided Entropic Neural Optimal Transport
petrmokrov/energy-guided-entropic-ot
•
•
Energy-based models (EBMs) are known in the Machine Learning community for decades.
Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation
livreq/imda
•
•
We further provide algorithm-dependent generalization bounds for these two settings, where the generalization is characterized by the mutual information between the parameters and the data.
Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks
pingzaiwang/Analysis4TNN
•
•
NeurIPS 2023
Our analysis indicates that the transformed low-rank parameterization can promisingly enhance robust generalization for t-NNs.
