{"total":22,"rows":[{"id":"2402.01868","title":"Challenges in Training PINNs: A Loss Landscape Perspective","created":"2024-02-02","cited_by_count":113,"area":null},{"id":"2501.18965","title":"The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training","created":"2025-01-31","cited_by_count":33,"area":null},{"id":"2507.11274","title":"Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime","created":"2025-07-15","cited_by_count":12,"area":null},{"id":"2310.00692","title":"A Theoretical Analysis of Noise Geometry in Stochastic Gradient Descent","created":"2023-10-01","cited_by_count":9,"area":null},{"id":"2410.12455","title":"Loss Landscape Characterization of Neural Networks without Over-Parametrization","created":"2024-10-16","cited_by_count":8,"area":null},{"id":"2306.11922","title":"No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths","created":"2023-06-20","cited_by_count":7,"area":null},{"id":"2410.08395","title":"Nesterov acceleration in benignly non-convex landscapes","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2502.17009","title":"Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2402.17890","title":"From Inverse Optimization to Feasibility to ERM","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2511.08417","title":"NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2406.05686","title":"Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning","created":"2024-06-09","cited_by_count":2,"area":null},{"id":"2505.17300","title":"Statistical Inference for Online Algorithms","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2604.09909","title":"Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2604.10373","title":"Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2408.01374","title":"Hybrid Coordinate Descent for Efficient Neural Network Learning Using Line Search and Gradient Descent","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2410.14885","title":"Beyond Discretization: Learning the Optimal Solution Path","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2412.06070","title":"Stochastic Gradient Descent Revisited","created":"2024-12-08","cited_by_count":0,"area":null},{"id":"2502.12329","title":"A Novel Unified Parametric Assumption for Nonconvex Optimization","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2605.14663","title":"Optimal Asymptotic Rates for (Stochastic) Gradient Descent under the Local PL-Condition: A Geometric Approach","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.25275","title":"Label-NTK Alignments and A Tighter Convergence Bound in the NTK Regime","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2605.29273","title":"A Theoretical and Experimental Study of a Novel Adaptive Learning Algorithm","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.29593","title":"How AI settled the complexity of the oldest SGD algorithm","created":"2026-06-28","cited_by_count":0,"area":null}],"next_cursor":null}