| Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective | Jun 24, 2023 | Graph Representation LearningLearning Theory | —Unverified | 0 |
| Scaling MLPs: A Tale of Inductive Bias | Jun 23, 2023 | Computational EfficiencyGPU | CodeCode Available | 1 |
| A primal-dual data-driven method for computational optical imaging with a photonic lantern | Jun 20, 2023 | Decision MakingLearning Theory | CodeCode Available | 0 |
| Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classification | Jun 15, 2023 | Learning Theory | —Unverified | 0 |
| Learning to Defend by Attacking (and Vice-Versa): Transfer of Learning in Cybersecurity Games | Jun 3, 2023 | Decision MakingLearning Theory | —Unverified | 0 |
| On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control | Jun 2, 2023 | Imitation LearningLearning Theory | —Unverified | 0 |
| Improving Energy Conserving Descent for Machine Learning: Theory and Practice | Jun 1, 2023 | Learning Theory | CodeCode Available | 0 |
| Hypothesis Transfer Learning with Surrogate Classification Losses: Generalization Bounds through Algorithmic Stability | May 31, 2023 | Binary ClassificationClassification | —Unverified | 0 |
| Benign Overfitting in Deep Neural Networks under Lazy Training | May 30, 2023 | Learning Theory | —Unverified | 0 |
| Embedding Inequalities for Barron-type Spaces | May 30, 2023 | Learning Theory | —Unverified | 0 |
| Improving Generalization of Complex Models under Unbounded Loss Using PAC-Bayes Bounds | May 30, 2023 | Learning Theory | —Unverified | 0 |
| How Does Information Bottleneck Help Deep Learning? | May 30, 2023 | Deep LearningGeneralization Bounds | CodeCode Available | 1 |
| How many samples are needed to leverage smoothness? | May 25, 2023 | Learning Theory | —Unverified | 0 |
| Data-driven Mixed Integer Optimization through Probabilistic Multi-variable Branching | May 21, 2023 | Learning Theory | —Unverified | 0 |
| How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features | May 20, 2023 | Learning TheoryMemorization | CodeCode Available | 0 |
| Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent | May 20, 2023 | Generalization BoundsLearning Theory | —Unverified | 0 |
| Supervised learning with probabilistic morphisms and kernel mean embeddings | May 10, 2023 | Learning Theory | —Unverified | 0 |
| Learnability with Time-Sharing Computational Resource Concerns | May 3, 2023 | Learning TheoryScheduling | —Unverified | 0 |
| The ART of Transfer Learning: An Adaptive and Robust Pipeline | Apr 30, 2023 | Learning TheorySparse Learning | —Unverified | 0 |
| Optimal PAC Bounds Without Uniform Convergence | Apr 18, 2023 | Binary ClassificationClassification | —Unverified | 0 |
| Challenges of learning multi-scale dynamics with AI weather models: Implications for stability and one solution | Apr 14, 2023 | Decision MakingDeep Learning | CodeCode Available | 0 |
| Depth Separation with Multilayer Mean-Field Networks | Apr 3, 2023 | Learning Theory | —Unverified | 0 |
| Bayesian Free Energy of Deep ReLU Neural Network in Overparametrized Cases | Mar 28, 2023 | Learning Theory | —Unverified | 0 |
| Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle | Mar 24, 2023 | Learning Theoryregression | CodeCode Available | 1 |
| Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent | Mar 23, 2023 | Learning Theory | —Unverified | 0 |
