Theory

On Non-Linear operators for Geometric Deep Learning NeurIPS 2022 On Scrambling Phenomena for Randomly Initialized Recurrent Networks NeurIPS 2022 On the Convergence of Certified Robust Training with Interval Bound Propagation ICLR 2022 On the difficulty of learning chaotic dynamics with RNNs NeurIPS 2022 On the Double Descent of Random Features Models Trained with SGD NeurIPS 2022 On the Effectiveness of Iterative Learning Control L4DC 2022 On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias NeurIPS 2022 On the equivalence of Oja’s algorithm and GROUSE AISTATS 2022 On the expressivity of bi-Lipschitz normalizing flows ACML 2022 On the generalization of learning algorithms that do not converge NeurIPS 2022 On the Implicit Bias of Gradient Descent for Temporal Extrapolation AISTATS 2022 On the non-universality of deep learning: quantifying the cost of symmetry NeurIPS 2022 On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features ICML 2022 On the Parameterization and Initialization of Diagonal State Space Models NeurIPS 2022 On the SDEs and Scaling Rules for Adaptive Gradient Algorithms NeurIPS 2022 On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels NeurIPS 2022 On the Symmetries of Deep Learning Models and their Internal Representations NeurIPS 2022 OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization CVPR 2022 Optimization-Based Separations for Neural Networks COLT 2022 Outlier Dimensions that Disrupt Transformers are Driven by Frequency EMNLP 2022 Outlier-Robust Sparse Estimation via Non-Convex Optimization NeurIPS 2022 Overparameterization of Deep ResNet: Zero Loss and Mean-field Analysis JMLR 2022 PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization NeurIPS 2022 Pay attention to your loss : understanding misconceptions about Lipschitz neural networks NeurIPS 2022 Phase Collapse in Neural Networks ICLR 2022