Theory

Norm-based Generalization Bounds for Sparse Neural Networks NeurIPS 2023 On Bridging the Gap between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization ICML 2023 On Data Scaling in Masked Image Modeling CVPR 2023 On double-descent in uncertainty quantification in overparametrized models AISTATS 2023 On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network ICML 2023 On Sparse Modern Hopfield Model NeurIPS 2023 On the Ability of Graph Neural Networks to Model Interactions Between Vertices NeurIPS 2023 On the Accelerated Noise-Tolerant Power Method AISTATS 2023 On the Convergence of Gradient Flow on Multi-layer Linear Models ICML 2023 On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters ICML 2023 On the Dynamics Under the Unhinged Loss and Beyond JMLR 2023 On the Expressive Flexibility of Self-Attention Matrices AAAI 2023 On the Expressivity Role of LayerNorm in Transformers’ Attention ACL 2023 On the impact of activation and normalization in obtaining isometric embeddings at initialization NeurIPS 2023 On the Stability and Generalization of Triplet Learning AAAI 2023 On the Training Instability of Shuffling SGD with Batch Normalization ICML 2023 Optimal Nonlinearities Improve Generalization Performance of Random Features ACML 2023 Optimal Sets and Solution Paths of ReLU Networks ICML 2023 Overparameterized Random Feature Regression with Nearly Orthogonal Data AISTATS 2023 Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck NeurIPS 2023 Perturbation Analysis of Neural Collapse ICML 2023 Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width NeurIPS 2023 Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets NeurIPS 2023 Precise Asymptotic Analysis of Deep Random Feature Models COLT 2023 Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs NeurIPS 2023