Theory

Norm-Based Generalisation Bounds for Deep Multi-Class Convolutional Neural Networks AAAI 2021 On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective CVPR 2021 On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting ICML 2021 On Linear Stability of SGD and Input-Smoothness of Neural Networks NeurIPS 2021 On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory AAAI 2021 On Monotonic Linear Interpolation of Neural Network Parameters ICML 2021 On Smoother Attributions using Neural Stochastic Differential Equations IJCAI 2021 On the Approximation Power of Two-Layer Networks of Random ReLUs COLT 2021 On the Dynamics of Training Attention Models ICLR 2021 On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks ICML 2021 On the Frequency Bias of Generative Models NeurIPS 2021 On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models ICML 2021 On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent ICML 2021 On the Random Conjugate Kernel and Neural Tangent Kernel ICML 2021 On the Sample Complexity of Learning under Geometric Stability NeurIPS 2021 On the Softmax Bottleneck of Recurrent Language Models AAAI 2021 On the Stochastic Stability of Deep Markov Models NeurIPS 2021 On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers ICLR 2021 On the Verification of Neural ODEs with Stochastic Guarantees AAAI 2021 Optimal Transport for Deep Generative Models: State of the Art and Research Challenges IJCAI 2021 Outside Computation with Superior Functions NAACL 2021 Overparameterization Improves Robustness to Covariate Shift in High Dimensions NeurIPS 2021 Parametric Complexity Bounds for Approximating PDEs with Neural Networks NeurIPS 2021 Passive Inter-Photon Imaging CVPR 2021 PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data ICML 2021