Theory

Convex Analysis of the Mean Field Langevin Dynamics AISTATS 2022 DAVINZ: Data Valuation using Deep Neural Networks at Initialization ICML 2022 Declarative nets that are equilibrium models ICLR 2022 Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis NeurIPS 2022 Deep Network Approximation in Terms of Intrinsic Parameters ICML 2022 Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry ICML 2022 Deep Representation Debiasing via Mutual Information Minimization and Maximization (Student Abstract) AAAI 2022 Defending Against Adversarial Attacks via Neural Dynamic System NeurIPS 2022 Demystifying the Neural Tangent Kernel From a Practical Perspective: Can It Be Trusted for Neural Architecture Search Without Training? CVPR 2022 Depth and Feature Learning are Provably Beneficial for Neural Network Discriminators COLT 2022 Differentially Private Learning with Margin Guarantees NeurIPS 2022 Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel NeurIPS 2022 Does the Data Induce Capacity Control in Deep Learning? ICML 2022 Does the Geometry of the Data Control the Geometry of Neural Predictions? (Student Abstract) AAAI 2022 Do Residual Neural Networks discretize Neural Ordinary Differential Equations? NeurIPS 2022 Effects of Data Geometry in Early Deep Learning NeurIPS 2022 Efficient MCMC Sampling with Dimension-Free Convergence Rate using ADMM-type Splitting JMLR 2022 Efficient Training of Low-Curvature Neural Networks NeurIPS 2022 Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation CVPR 2022 Embedded Ensembles: infinite width limit and operating regimes AISTATS 2022 Emergent Structures and Training Dynamics in Large Language Models ACL 2022 Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width NeurIPS 2022 Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization NeurIPS 2022 Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions With Superior OOD Generalization CVPR 2022 Evolution of Neural Tangent Kernels under Benign and Adversarial Training NeurIPS 2022