spectral norm

Confusion-Aware Spectral Regularizer for Long-Tailed Recognition CVPR 2026 On Purely Private Covariance Estimation ALT 2026 Enhancing Robust Fairness via Confusional Spectral Regularization ICLR 2025 On Generalization Bounds for Neural Networks with Low Rank Layers ALT 2025 Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints ICCV 2025 On the Generalization of Equivariant Graph Neural Networks ICML 2024 Spectrum Extraction and Clipping for Implicitly Linear Layers AISTATS 2024 Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers ECCV 2024 Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration ICML 2023 Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian Distributions COLT 2023 Intractability of Learning the Discrete Logarithm with Gradient-Based Methods ACML 2023 Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function ICLR 2023 KDEformer: Accelerating Transformers via Kernel Density Estimation ICML 2023 SSDA: Secure Source-Free Domain Adaptation ICCV 2023 Understanding Hessian Alignment for Domain Generalization ICCV 2023 Conditional Linear Regression for Heterogeneous Covariances AISTATS 2022 New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma NeurIPS 2022 The alignment property of SGD noise and how it helps select flat minima: A stability analysis NeurIPS 2022 The Sample Complexity of One-Hidden-Layer Neural Networks NeurIPS 2022 A Law of Robustness for Two-Layers Neural Networks COLT 2021 A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks ICLR 2021 Robust Bayesian Neural Networks by Spectral Expectation Bound Regularization CVPR 2021 Entrywise convergence of iterative methods for eigenproblems NeurIPS 2020 On Generalization Bounds of a Family of Recurrent Neural Networks AISTATS 2020 The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks NeurIPS 2020