{"total":14,"rows":[{"id":"2110.15412","title":"Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize","created":"2021-10-28","cited_by_count":22,"area":null},{"id":"2402.17722","title":"Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence","created":"2024-02-27","cited_by_count":11,"area":null},{"id":"2406.01870","title":"Understanding Stochastic Natural Gradient Variational Inference","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2306.14522","title":"Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2306.16484","title":"Towards a Better Theoretical Understanding of Independent Subnetwork Training","created":"2023-06-28","cited_by_count":6,"area":null},{"id":"2104.14562","title":"Stochastic Mirror Descent for Low-Rank Tensor Decomposition Under Non-Euclidean Losses","created":"2021-04-29","cited_by_count":4,"area":null},{"id":"2510.19163","title":"Natural Gradient VI: Guarantees for Non-Conjugate Models","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2311.02557","title":"Fast Minimization of Expected Logarithmic Loss via Stochastic Dual Averaging","created":"2023-11-05","cited_by_count":1,"area":null},{"id":"2311.16706","title":"Sinkhorn Flow: A Continuous-Time Framework for Understanding and Generalizing the Sinkhorn Algorithm","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2603.16042","title":"Shuffling the Stochastic Mirror Descent via Dual Lipschitz Continuity and Kernel Conditioning","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2604.00683","title":"Convergence of projected stochastic natural gradient variational inference for various step size and sample or batch size schedules","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2111.06826","title":"Convergence Rates for the MAP of an Exponential Family and Stochastic Mirror Descent -- an Open Problem","created":"2021-11-12","cited_by_count":0,"area":null},{"id":"2111.07866","title":"Mitigating Divergence of Latent Factors via Dual Ascent for Low Latency Event Prediction Models","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2207.08195","title":"SPIRAL: A superlinearly convergent incremental proximal algorithm for nonconvex finite sum minimization","created":"2022-07-17","cited_by_count":0,"area":null}],"next_cursor":null}