{"total":32,"rows":[{"id":"2106.09524","title":"Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity","created":"2021-06-17","cited_by_count":110,"area":null},{"id":"2309.12659","title":"OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling","created":"2023-09-22","cited_by_count":74,"area":null},{"id":"2304.00488","title":"Saddle-to-Saddle Dynamics in Diagonal Linear Networks","created":"2023-04-02","cited_by_count":57,"area":null},{"id":"2302.08982","title":"(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability","created":"2023-02-17","cited_by_count":36,"area":null},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2206.09841","title":"Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation","created":"2022-06-20","cited_by_count":29,"area":null},{"id":"2103.06263","title":"Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution","created":"2021-03-10","cited_by_count":13,"area":null},{"id":"2105.13831","title":"Implicit Regularization in Matrix Sensing via Mirror Descent","created":"2021-05-28","cited_by_count":11,"area":null},{"id":"2205.01385","title":"Smooth over-parameterized solvers for non-smooth structured optimization","created":"2022-05-03","cited_by_count":11,"area":null},{"id":"2205.15235","title":"Non-convex online learning via algorithmic equivalence","created":"2022-05-30","cited_by_count":11,"area":null},{"id":"2403.05293","title":"Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks","created":"2024-03-08","cited_by_count":9,"area":null},{"id":"2106.03589","title":"Nonparametric adaptive control and prediction: theory and randomized algorithms","created":"2021-06-07","cited_by_count":8,"area":null},{"id":"2207.04387","title":"Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes","created":"2022-07-10","cited_by_count":7,"area":null},{"id":"2110.07807","title":"Provable Regret Bounds for Deep Online Learning and Control","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2406.00655","title":"Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2305.19394","title":"Synaptic Weight Distributions Depend on the Geometry of Plasticity","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2208.04065","title":"Optimistic Optimisation of Composite Objective with Exponentiated Update","created":"2022-08-08","cited_by_count":3,"area":null},{"id":"2303.04397","title":"The Lie-Group Bayesian Learning Rule","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2503.08748","title":"Mirror Descent and Novel Exponentiated Gradient Algorithms Using Trace-Form Entropies and Deformed Logarithms","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2211.02106","title":"Federated Hypergradient Descent","created":"2022-11-03","cited_by_count":2,"area":null},{"id":"2502.17500","title":"Generalized Euler Logarithm and its Applications in Machine Learning: Natural Gradient, Backpropagation, Generalized EG, Mirror Descent and OLPS","created":"2025-02-21","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":"2506.17768","title":"Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2111.09982","title":"Second-Order Mirror Descent: Convergence in Games Beyond Averaging and Discounting","created":"2021-11-18","cited_by_count":1,"area":null},{"id":"2506.13984","title":"Mirror Descent Using the Tempesta Generalized Multi-parametric Logarithms","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2210.16371","title":"Distributed Black-box Attack: Do Not Overestimate Black-box Attacks","created":"2022-10-28","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":"2508.12773","title":"Online Ensemble Transformer for Accurate Cloud Workload Forecasting in Predictive Auto-Scaling","created":"2025-08-18","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":"2603.18157","title":"Learning-Augmented Algorithms for $k$-median via Online Learning","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2609.34756","title":"Statistical Benefits of Fine-Tuning from Pretrained Initialization in Diagonal Linear Networks","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}