Theory

Learnability of high-dimensional targets by two-parameter models and gradient flow NeurIPS 2024 Learned Transformer Position Embeddings Have a Low-Dimensional Structure ACL 2024 Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks NeurIPS 2024 Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees NeurIPS 2024 Learning symmetries via weight-sharing with doubly stochastic tensors NeurIPS 2024 Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks JMLR 2024 Length independent PAC-Bayes bounds for Simple RNNs AISTATS 2024 Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures AISTATS 2024 Light Unbalanced Optimal Transport NeurIPS 2024 Linear attention is (maybe) all you need (to understand Transformer optimization) ICLR 2024 Local to Global: Learning Dynamics and Effect of Initialization for Transformers NeurIPS 2024 Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk NeurIPS 2024 Loss Landscape Characterization of Neural Networks without Over-Parametrization NeurIPS 2024 Lyapunov-Stable Deep Equilibrium Models AAAI 2024 Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input NeurIPS 2024 Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks UAI 2024 Model Collapse Demystified: The Case of Regression NeurIPS 2024 Multi-layer random features and the approximation power of neural networks UAI 2024 Multiple Descent in the Multiple Random Feature Model JMLR 2024 Neural Collapse To Multiple Centers For Imbalanced Data NeurIPS 2024 Neural Conditional Probability for Uncertainty Quantification NeurIPS 2024 NeuralFluid: Nueral Fluidic System Design and Control with Differentiable Simulation NeurIPS 2024 Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit NeurIPS 2024 Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK JMLR 2024 Neural Redshift: Random Networks are not Random Functions CVPR 2024