{"total":31,"rows":[{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166,"area":null},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73,"area":null},{"id":"2102.09393","title":"On the Convergence of Step Decay Step-Size for Stochastic Optimization","created":"2021-02-18","cited_by_count":21,"area":null},{"id":"2108.03947","title":"On the Hyperparameters in Stochastic Gradient Descent with Momentum","created":"2021-08-09","cited_by_count":9,"area":null},{"id":"2209.14501","title":"On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2110.05960","title":"Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations","created":"2021-10-11","cited_by_count":8,"area":null},{"id":"2209.08862","title":"Gradient Norm Minimization of Nesterov Acceleration: $o(1/k^3)$","created":"2022-09-19","cited_by_count":8,"area":null},{"id":"2407.06183","title":"Stepping on the Edge: Curvature Aware Learning Rate Tuners","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2501.12243","title":"FOCUS: First Order Concentrated Updating Scheme","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2303.15634","title":"Learning Rate Schedules in the Presence of Distribution Shift","created":"2023-03-27","cited_by_count":7,"area":null},{"id":"2311.15587","title":"Quantum Langevin Dynamics for Optimization","created":"2023-11-27","cited_by_count":7,"area":null},{"id":"2410.22113","title":"Where Do Large Learning Rates Lead Us?","created":"2024-10-29","cited_by_count":6,"area":null},{"id":"2210.11452","title":"Global Convergence of SGD On Two Layer Neural Nets","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2402.08606","title":"Arbitrary Polynomial Separations in Trainable Quantum Machine Learning","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2106.16200","title":"Revisiting the Effects of Stochasticity for Hamiltonian Samplers","created":"2021-06-30","cited_by_count":3,"area":null},{"id":"2309.09258","title":"Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2106.02888","title":"Bandwidth-based Step-Sizes for Non-Convex Stochastic Optimization","created":"2021-06-05","cited_by_count":2,"area":null},{"id":"2201.10245","title":"On Uniform Boundedness Properties of SGD and its Momentum Variants","created":"2022-01-25","cited_by_count":2,"area":null},{"id":"2311.00811","title":"A quantum-classical performance separation in nonconvex optimization","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2510.12013","title":"Statistical Guarantees for High-Dimensional Stochastic Gradient Descent","created":"2025-10-13","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":"2304.14642","title":"On Underdamped Nesterov's Acceleration","created":"2023-04-28","cited_by_count":1,"area":null},{"id":"2406.13971","title":"Complex fractal trainability boundary can arise from trivial non-convexity","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2503.10428","title":"Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2508.07397","title":"A Spin Glass Characterization of Neural Networks","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2603.12552","title":"Asymptotic and Finite-Time Guarantees for Langevin-Based Temperature Annealing in InfoNCE","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2605.07959","title":"Convergent Stochastic Training of Multi-Headed Attention and Understanding LoRA","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2101.02625","title":"Boundary Conditions for Linear Exit Time Gradient Trajectories Around Saddle Points: Analysis and Algorithm","created":"2021-01-07","cited_by_count":0,"area":null},{"id":"2404.14358","title":"A General Continuous-Time Formulation of Stochastic ADMM and Its Variants","created":"2024-04-22","cited_by_count":0,"area":null},{"id":"2505.14670","title":"Quantum Optimization via Gradient-Based Hamiltonian Descent","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2604.13022","title":"Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent","created":"2026-04-14","cited_by_count":0,"area":null}],"next_cursor":null}