{"total":29,"rows":[{"id":"2402.02347","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","created":"2024-02-04","cited_by_count":52,"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":"2403.11871","title":"The Real Tropical Geometry of Neural Networks","created":"2024-03-18","cited_by_count":24,"area":null},{"id":"2305.16534","title":"Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression","created":"2023-05-25","cited_by_count":18,"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":"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":"2306.00119","title":"Optimal Sets and Solution Paths of ReLU Networks","created":"2023-05-31","cited_by_count":10,"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":"2302.04753","title":"Efficient displacement convex optimization with particle gradient descent","created":"2023-02-09","cited_by_count":5,"area":null},{"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":"2411.01088","title":"CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks","created":"2024-11-02","cited_by_count":4,"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":"2603.22030","title":"On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors","created":"2026-03-23","cited_by_count":3,"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":"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":"2407.16800","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":"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":"2406.02806","title":"Randomized Geometric Algebra Methods for Convex Neural Networks","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2406.17954","title":"Why Line Search when you can Plane Search? SO-Friendly Neural Networks allow Per-Iteration Optimization of Learning and Momentum Rates for Every Layer","created":"2024-06-25","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":"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":"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":"2605.23235","title":"Convex Low-resource Accent-Robust Language Detection in Speech Recognition","created":"2026-05-22","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}],"next_cursor":null}