Theory

Fine-grained Expressivity of Graph Neural Networks NeurIPS 2023 Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron ICML 2023 Focus Your Attention (with Adaptive IIR Filters) EMNLP 2023 FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation ICML 2023 Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods ICML 2023 Generalization and Estimation Error Bounds for Model-based Neural Networks ICLR 2023 Generalization bounds for neural ordinary differential equations and deep residual networks NeurIPS 2023 GEQ: Gaussian Kernel Inspired Equilibrium Models NeurIPS 2023 Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization NeurIPS 2023 Global optimality of Elman-type RNNs in the mean-field regime ICML 2023 Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space ICML 2023 Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023 Greedy Poisson Rejection Sampling NeurIPS 2023 Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale. ACL 2023 How Does Information Bottleneck Help Deep Learning? ICML 2023 How much does Initialization Affect Generalization? ICML 2023 How Powerful are Shallow Neural Networks with Bandlimited Random Weights? ICML 2023 Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping JMLR 2023 Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data ICLR 2023 Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data NeurIPS 2023 Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions ICLR 2023 Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent ICLR 2023 Initialization Noise in Image Gradients and Saliency Maps CVPR 2023 Instance-Dependent Generalization Bounds via Optimal Transport JMLR 2023 Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings ACL 2023