{"total":98,"rows":[{"id":"2103.01516","title":"Private Stochastic Convex Optimization: Optimal Rates in $\\ell_1$ Geometry","created":"2021-03-02","cited_by_count":83,"area":null},{"id":"2103.04737","title":"Low-Rank Sinkhorn Factorization","created":"2021-03-08","cited_by_count":67,"area":null},{"id":"2206.05825","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","created":"2022-06-12","cited_by_count":66,"area":null},{"id":"2106.01128","title":"Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs","created":"2021-06-02","cited_by_count":61,"area":null},{"id":"2206.08873","title":"Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM","created":"2022-06-17","cited_by_count":34,"area":null},{"id":"2205.12808","title":"Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently","created":"2022-05-25","cited_by_count":26,"area":null},{"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":"2111.11309","title":"No-Regret Dynamics in the Fenchel Game: A Unified Framework for Algorithmic Convex Optimization","created":"2021-11-22","cited_by_count":20,"area":null},{"id":"2208.05888","title":"Super-Universal Regularized Newton Method","created":"2022-08-11","cited_by_count":20,"area":null},{"id":"2303.12277","title":"Stochastic Nonsmooth Convex Optimization with Heavy-Tailed Noises: High-Probability Bound, In-Expectation Rate and Initial Distance Adaptation","created":"2023-03-22","cited_by_count":20,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2110.12347","title":"Acceleration in Distributed Optimization under Similarity","created":"2021-10-24","cited_by_count":17,"area":null},{"id":"2202.09674","title":"Generalized Optimistic Methods for Convex-Concave Saddle Point Problems","created":"2022-02-19","cited_by_count":16,"area":null},{"id":"2310.11914","title":"A connection between Tempering and Entropic Mirror Descent","created":"2023-10-18","cited_by_count":16,"area":null},{"id":"2106.11428","title":"Local convexity of the TAP free energy and AMP convergence for Z2-synchronization","created":"2021-06-21","cited_by_count":15,"area":null},{"id":"2202.04640","title":"Sharper Rates for Separable Minimax and Finite Sum Optimization via Primal-Dual Extragradient Methods","created":"2022-02-09","cited_by_count":15,"area":null},{"id":"2410.18965","title":"On the Crucial Role of Initialization for Matrix Factorization","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2306.13853","title":"A Unified Approach to Controlling Implicit Regularization via Mirror Descent","created":"2023-06-24","cited_by_count":14,"area":null},{"id":"2407.15693","title":"Fisher-Rao Gradient Flow: Geodesic Convexity and Functional Inequalities","created":"2024-07-22","cited_by_count":13,"area":null},{"id":"2405.20250","title":"Entropy annealing for policy mirror descent in continuous time and space","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2304.07504","title":"Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis","created":"2023-04-15","cited_by_count":11,"area":null},{"id":"2305.13946","title":"Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness","created":"2023-05-23","cited_by_count":11,"area":null},{"id":"2312.08823","title":"Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithm","created":"2023-12-14","cited_by_count":11,"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":"2408.09074","title":"Gradient-Variation Online Learning under Generalized Smoothness","created":"2024-08-17","cited_by_count":11,"area":null},{"id":"2305.07730","title":"Learning in Inverse Optimization: Incenter Cost, Augmented Suboptimality Loss, and Algorithms","created":"2023-05-12","cited_by_count":10,"area":null},{"id":"2101.11041","title":"Complementary Composite Minimization, Small Gradients in General Norms, and Applications","created":"2021-01-26","cited_by_count":9,"area":null},{"id":"2207.08257","title":"Uniform Stability for First-Order Empirical Risk Minimization","created":"2022-07-17","cited_by_count":8,"area":null},{"id":"2303.18047","title":"Differentially Private Stochastic Convex Optimization in (Non)-Euclidean Space Revisited","created":"2023-03-31","cited_by_count":8,"area":null},{"id":"2406.01870","title":"Understanding Stochastic Natural Gradient Variational Inference","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2210.00997","title":"Online Self-Concordant and Relatively Smooth Minimization, With Applications to Online Portfolio Selection and Learning Quantum States","created":"2022-10-03","cited_by_count":7,"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":"2408.11620","title":"Annealed Sinkhorn for Optimal Transport: convergence, regularization path and debiasing","created":"2024-08-21","cited_by_count":7,"area":null},{"id":"2507.11461","title":"Deep Equilibrium models for Poisson Imaging Inverse problems via Mirror Descent","created":"2025-07-15","cited_by_count":7,"area":null},{"id":"2108.06808","title":"Implicit Regularization of Bregman Proximal Point Algorithm and Mirror Descent on Separable Data","created":"2021-08-15","cited_by_count":6,"area":null},{"id":"2205.03202","title":"Perseus: A Simple and Optimal High-Order Method for Variational Inequalities","created":"2022-05-06","cited_by_count":5,"area":null},{"id":"2206.01209","title":"Accelerated first-order methods for convex optimization with locally Lipschitz continuous gradient","created":"2022-06-02","cited_by_count":5,"area":null},{"id":"2101.00935","title":"First-Order Methods for Convex Optimization","created":"2021-01-04","cited_by_count":4,"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":"2107.04395","title":"Block Alternating Bregman Majorization Minimization with Extrapolation","created":"2021-07-09","cited_by_count":4,"area":null},{"id":"2107.08011","title":"Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2112.11928","title":"A Stochastic Bregman Primal-Dual Splitting Algorithm for Composite Optimization","created":"2021-12-22","cited_by_count":4,"area":null},{"id":"2202.02388","title":"Bregman Plug-and-Play Priors","created":"2022-02-04","cited_by_count":3,"area":null},{"id":"2305.15249","title":"Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2402.13530","title":"Best of Many in Both Worlds: Online Resource Allocation with Predictions under Unknown Arrival Model","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2405.10754","title":"Stable Phase Retrieval with Mirror Descent","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2506.13710","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2507.15264","title":"On exploration of an interior mirror descent flow for stochastic nonconvex constrained problem","created":"2025-07-21","cited_by_count":3,"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":"2606.00520","title":"In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2202.12843","title":"Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions","created":"2022-02-25","cited_by_count":2,"area":null},{"id":"2210.09248","title":"Provable Phase Retrieval with Mirror Descent","created":"2022-10-17","cited_by_count":2,"area":null},{"id":"2402.08106","title":"Mirror Descent-Ascent for mean-field min-max problems","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2412.16414","title":"Accelerated Methods with Compressed Communications for Distributed Optimization Problems under Data Similarity","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2502.11033","title":"Convergence of Policy Mirror Descent Beyond Compatible Function Approximation","created":"2025-02-16","cited_by_count":2,"area":null},{"id":"2504.02618","title":"Variational Online Mirror Descent for Robust Learning in Schr\\\"odinger Bridge","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2506.12648","title":"Glocal Smoothness: Line search and adaptive step sizes can help in theory too!","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2509.08739","title":"Bregman Douglas-Rachford Splitting Method","created":"2025-09-10","cited_by_count":2,"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":"2311.15404","title":"Applying statistical learning theory to deep learning","created":"2023-11-26","cited_by_count":1,"area":null},{"id":"2507.16008","title":"Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point Reformulation","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2511.22283","title":"The Hidden Cost of Approximation in Online Mirror Descent","created":"2025-11-27","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":"2608.01658","title":"Non-KKT Accumulation in Entropic Mirror Descent","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2107.01106","title":"Screening for a Reweighted Penalized Conditional Gradient Method","created":"2021-07-02","cited_by_count":0,"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":"2112.00565","title":"On Mixing Times of Metropolized Algorithm With Optimization Step (MAO) : A New Framework","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2201.07657","title":"Multiblock ADMM for nonsmooth nonconvex optimization with nonlinear coupling constraints","created":"2022-01-19","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},{"id":"2212.06081","title":"Fast Learning of Multidimensional Hawkes Processes via Frank-Wolfe","created":"2022-12-12","cited_by_count":0,"area":null},{"id":"2305.09046","title":"Convex optimization over a probability simplex","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2306.10587","title":"Acceleration in Policy Optimization","created":"2023-06-18","cited_by_count":0,"area":null},{"id":"2306.17470","title":"Oblivious Stochastic Composite Optimization","created":"2023-06-30","cited_by_count":0,"area":null},{"id":"2307.00247","title":"Safe Screening for Unbalanced Optimal Transport","created":"2023-07-01","cited_by_count":0,"area":null},{"id":"2403.10232","title":"Matrix Completion via Nonsmooth Regularization of Fully Connected Neural Networks","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2404.16505","title":"Efficient algorithms for regularized Poisson Non-negative Matrix Factorization","created":"2024-04-25","cited_by_count":0,"area":null},{"id":"2407.03294","title":"NewVEM: A Newton Vertex Exchange Method for a Class of Constrained Self-Concordant Minimization Problems","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2412.13928","title":"Subspace Langevin Monte Carlo","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2505.02614","title":"Entropic Mirror Descent for Linear Systems: Polyak's Stepsize and Implicit Bias","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2601.08614","title":"Accelerated Methods with Complexity Separation Under Data Similarity for Federated Learning Problems","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2603.03578","title":"Transport Clustering: Solving Low-Rank Optimal Transport via Clustering","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.08651","title":"Group Entropies and Mirror Duality: A Class of Flexible Mirror Descent Updates for Machine Learning","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.11989","title":"On-Average Stability of Multipass Preconditioned SGD and Effective Dimension","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.12838","title":"A New Kernel Regularity Condition for Distributed Mirror Descent: Broader Coverage and Simpler Analysis","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.31426","title":"Self-Tuning Regularization for Image Scanning Microscopy","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.11431","title":"Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.20082","title":"Beyond Averaging in John Ellipsoid Approximation: High-Accuracy Algorithms in the Leverage-Score Model","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.27767","title":"Difference of Convex Programming in the Wasserstein Space with Applications to MMD Optimization","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.27476","title":"Entropy-Smooth Convex Optimization Cannot Be Accelerated","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.03001","title":"Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.07248","title":"Establishing Boundary KKT Convergence of Mirror Descent through Reparameterization","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.08642","title":"Exact Rank-Space KL Projection for Shared-Marginal Low-Rank Factors: Application to Doubly Stochastic Clustering","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.11479","title":"Convergence Guarantees of Gradient Descent for Neural Networks via Generalized Lipschitz Smoothness","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.12009","title":"Adaptive Bregman Proximal Stochastic Gradient with a Stabilized Barzilai--Borwein Step Size","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.22834","title":"Mirror descent algorithms with logarithmic barriers","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.33194","title":"Orthogonal Witness Control for Muon Optimization via Sigmoid Spectral Reshaping","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.39301","title":"Generalized Geometry Block Proximal Linearized Method for Multiblock Nonconvex and Nonsmooth Optimization","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}