{"total":98,"rows":[{"id":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86,"area":null},{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53,"area":null},{"id":"2402.02347","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","created":"2024-02-04","cited_by_count":52,"area":null},{"id":"2402.11867","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","created":"2024-02-19","cited_by_count":48,"area":null},{"id":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","cited_by_count":39,"area":null},{"id":"2202.01331","title":"Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions","created":"2022-02-02","cited_by_count":31,"area":null},{"id":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30,"area":null},{"id":"2110.05518","title":"Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs","created":"2021-10-11","cited_by_count":25,"area":null},{"id":"2303.17045","title":"Training Neural Networks is NP-Hard in Fixed Dimension","created":"2023-03-29","cited_by_count":23,"area":null},{"id":"2105.08675","title":"The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality","created":"2021-05-18","cited_by_count":22,"area":null},{"id":"2103.01499","title":"Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization","created":"2021-03-02","cited_by_count":21,"area":null},{"id":"2301.09554","title":"Deep Learning Meets Sparse Regularization: A Signal Processing Perspective","created":"2023-01-23","cited_by_count":21,"area":null},{"id":"2304.05752","title":"Function Space and Critical Points of Linear Convolutional Networks","created":"2023-04-12","cited_by_count":19,"area":null},{"id":"2102.12238","title":"Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm","created":"2021-02-24","cited_by_count":18,"area":null},{"id":"2209.04121","title":"Fast Neural Kernel Embeddings for General Activations","created":"2022-09-09","cited_by_count":18,"area":null},{"id":"2201.01965","title":"Efficient Global Optimization of Two-Layer ReLU Networks: Quadratic-Time Algorithms and Adversarial Training","created":"2022-01-06","cited_by_count":15,"area":null},{"id":"2101.02429","title":"Neural Spectrahedra and Semidefinite Lifts: Global Convex Optimization of Polynomial Activation Neural Networks in Fully Polynomial-Time","created":"2021-01-07","cited_by_count":14,"area":null},{"id":"2107.05680","title":"Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions","created":"2021-07-12","cited_by_count":14,"area":null},{"id":"2110.09548","title":"Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks","created":"2021-10-18","cited_by_count":14,"area":null},{"id":"2211.11052","title":"Convexifying Transformers: Improving optimization and understanding of transformer networks","created":"2022-11-20","cited_by_count":12,"area":null},{"id":"2110.06488","title":"The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program","created":"2021-10-13","cited_by_count":11,"area":null},{"id":"2402.03625","title":"Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2204.09664","title":"Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?","created":"2022-04-20","cited_by_count":10,"area":null},{"id":"2306.00119","title":"Optimal Sets and Solution Paths of ReLU Networks","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2110.06482","title":"Parallel Deep Neural Networks Have Zero Duality Gap","created":"2021-10-13","cited_by_count":9,"area":null},{"id":"2205.13098","title":"Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization","created":"2022-05-26","cited_by_count":9,"area":null},{"id":"2303.03382","title":"Globally Optimal Training of Neural Networks with Threshold Activation Functions","created":"2023-03-06","cited_by_count":9,"area":null},{"id":"2505.12455","title":"AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2301.12540","title":"Implicit Regularization for Group Sparsity","created":"2023-01-29","cited_by_count":8,"area":null},{"id":"2305.15598","title":"ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2404.18769","title":"Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2206.00257","title":"CoNSoLe: Convex Neural Symbolic Learning","created":"2022-06-01","cited_by_count":7,"area":null},{"id":"2312.12657","title":"The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2402.01965","title":"Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization","created":"2024-02-03","cited_by_count":7,"area":"diffusion"},{"id":"2105.01420","title":"Training Quantized Neural Networks to Global Optimality via Semidefinite Programming","created":"2021-05-04","cited_by_count":6,"area":null},{"id":"2506.19031","title":"When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets","created":"2025-06-23","cited_by_count":6,"area":"diffusion"},{"id":"2306.10486","title":"On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization","created":"2023-06-18","cited_by_count":5,"area":null},{"id":"2411.13525","title":"Geometric Algebra Planes: Convex Implicit Neural Volumes","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2602.19926","title":"Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models","created":"2026-02-23","cited_by_count":5,"area":"lr"},{"id":"2105.12237","title":"Practical Convex Formulation of Robust One-hidden-layer Neural Network Training","created":"2021-05-25","cited_by_count":4,"area":null},{"id":"2305.16474","title":"FairDP: Certified Fairness with Differential Privacy","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2309.16512","title":"From Complexity to Clarity: Analytical Expressions of Deep Neural Network Weights via Clifford's Geometric Algebra and Convexity","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2411.01088","title":"CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks","created":"2024-11-02","cited_by_count":4,"area":null},{"id":"2501.15941","title":"SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning","created":"2025-01-27","cited_by_count":4,"area":null},{"id":"2209.15265","title":"Overparameterized ReLU Neural Networks Learn the Simplest Models: Neural Isometry and Exact Recovery","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2210.00176","title":"A Combinatorial Perspective on the Optimization of Shallow ReLU Networks","created":"2022-10-01","cited_by_count":3,"area":null},{"id":"2211.07675","title":"On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2402.08808","title":"Depth Separation in Norm-Bounded Infinite-Width Neural Networks","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2507.20351","title":"Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights","created":"2025-07-27","cited_by_count":3,"area":null},{"id":"2106.04795","title":"Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off","created":"2021-06-09","cited_by_count":2,"area":null},{"id":"2112.11157","title":"Integral representations of shallow neural network with Rectified Power Unit activation function","created":"2021-12-20","cited_by_count":2,"area":null},{"id":"2210.03069","title":"PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2311.10972","title":"Polynomial-Time Solutions for ReLU Network Training: A Complexity Classification via Max-Cut and Zonotopes","created":"2023-11-18","cited_by_count":2,"area":null},{"id":"2405.11775","title":"Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques","created":"2024-05-20","cited_by_count":2,"area":null},{"id":"2407.04884","title":"Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2407.08169","title":"The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2407.16800","title":"Wasserstein Distributionally Robust Shallow Convex Neural Networks","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2411.06848","title":"Generative Feature Training of Thin 2-Layer Networks","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2601.16884","title":"Multigrade Neural Network Approximation","created":"2026-01-23","cited_by_count":2,"area":null},{"id":"2202.08876","title":"An alternative approach to train neural networks using monotone variational inequality","created":"2022-02-17","cited_by_count":1,"area":null},{"id":"2205.14056","title":"Dual Convexified Convolutional Neural Networks","created":"2022-05-27","cited_by_count":1,"area":null},{"id":"2208.07464","title":"An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models","created":"2022-08-15","cited_by_count":1,"area":null},{"id":"2304.02972","title":"Training a Two Layer ReLU Network Analytically","created":"2023-04-06","cited_by_count":1,"area":null},{"id":"2309.15096","title":"Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs","created":"2023-09-26","cited_by_count":1,"area":null},{"id":"2403.01046","title":"A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features","created":"2024-03-02","cited_by_count":1,"area":null},{"id":"2405.14033","title":"Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimization","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2406.02806","title":"Randomized Geometric Algebra Methods for Convex Neural Networks","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2410.02145","title":"Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2505.22578","title":"Favorability of Loss Landscape with Weight Decay Requires Both Large Overparametrization and Initialization","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.10623","title":"Flows and Diffusions on the Neural Manifold","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2602.19172","title":"Online Realizable Regression and Applications for ReLU Networks","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2603.23831","title":"Unveiling Hidden Convexity in Deep Learning: a Sparse Signal Processing Perspective","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2304.06959","title":"Convex Dual Theory Analysis of Two-Layer Convolutional Neural Networks with Soft-Thresholding","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2305.04433","title":"Accelerated Algorithms for a Class of Optimization Problems with Equality and Box Constraints","created":"2023-05-08","cited_by_count":0,"area":null},{"id":"2402.19212","title":"Deep Reinforcement Learning: A Convex Optimization Approach","created":"2024-02-29","cited_by_count":0,"area":"deeprl"},{"id":"2408.12119","title":"Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2408.15969","title":"Stability of Primal-Dual Gradient Flow Dynamics for Multi-Block Convex Optimization Problems","created":"2024-08-28","cited_by_count":0,"area":null},{"id":"2409.12493","title":"ConvexECG: Lightweight and Explainable Neural Networks for Personalized, Continuous Cardiac Monitoring","created":"2024-09-19","cited_by_count":0,"area":null},{"id":"2410.06567","title":"Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2504.12918","title":"Sliced-Wasserstein Distance-based Data Selection","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2505.21791","title":"Global Minimizers of $\\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2507.01044","title":"Asymptotic convexity of wide and shallow neural networks","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2508.17783","title":"Algebraic Approach to Ridge-Regularized Mean Squared Error Minimization in Minimal ReLU Neural Network","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2509.20323","title":"A Recovery Guarantee for Sparse Neural Networks","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.23455","title":"SGFusion: Stochastic Geographic Gradient Fusion in Federated Learning","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2602.19017","title":"Why ReLU? A Bit-Model Dichotomy for Deep Network Training","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2605.01897","title":"How Label Imbalance Shapes Geometry: A General Spectral Analysis of Multi-Label Neural Collapse","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.17692","title":"Exact Convex Reformulations of Linear Neural Networks via Completely Positive Lifting","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.23235","title":"Convex Low-resource Accent-Robust Language Detection in Speech Recognition","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.23244","title":"Convex Optimization for Alignment and Preference Learning on a Single GPU","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2605.25134","title":"Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.19652","title":"Convex training of Lipschitz-regularized shallow neural networks","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.00138","title":"MG-SpaIR: Multi-grade Sparse-guided Implicit Representation for Training-Data-Free Image Restoration","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.16720","title":"Effects of width-dependent model hyperparameters and $\\ell_2$-regularization on the loss landscape of two-layer ReLU networks","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2610.01728","title":"Removing spurious minima for planar features by skip connections","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04533","title":"Weight Decay and Neuron Condensation: A Three-Stage Analysis of Two-Layer ReLU Networks","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04670","title":"A Tropical Geometry View of Forgetting: A Per-Unit Projector for Knowledge-Preserving Fine-Tuning","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}