{"total":40,"rows":[{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2502.04664","title":"Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data","created":"2025-02-07","cited_by_count":41,"area":null},{"id":"2103.04490","title":"Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems","created":"2021-03-07","cited_by_count":39,"area":null},{"id":"2102.12567","title":"Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks","created":"2021-02-24","cited_by_count":32,"area":null},{"id":"2201.12522","title":"Continual Learning with Recursive Gradient Optimization","created":"2022-01-29","cited_by_count":32,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"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":"2408.15417","title":"Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations","created":"2024-08-27","cited_by_count":24,"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":"2204.06716","title":"Control-oriented meta-learning","created":"2022-04-14","cited_by_count":17,"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":"2402.18551","title":"Implicit Optimization Bias of Next-Token Prediction in Linear Models","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2207.13853","title":"ORFit: One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares","created":"2022-07-28","cited_by_count":12,"area":null},{"id":"2410.14581","title":"Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection","created":"2024-10-18","cited_by_count":9,"area":null},{"id":"2409.15267","title":"Peer-to-Peer Learning Dynamics of Wide Neural Networks","created":"2024-09-23","cited_by_count":8,"area":null},{"id":"2210.01881","title":"Tractable Uncertainty-Aware Meta-Learning","created":"2022-10-04","cited_by_count":4,"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":"2505.04757","title":"Primal-dual algorithm for contextual stochastic combinatorial optimization","created":"2025-05-07","cited_by_count":4,"area":null},{"id":"2506.00630","title":"Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2304.10317","title":"Adaptive Consensus Optimization Method for GANs","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2410.14158","title":"A Mirror Descent Perspective of Smoothed Sign Descent","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2602.03535","title":"Sparse Training of Neural Networks based on Multilevel Mirror Descent","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2202.10788","title":"Explicit Regularization via Regularizer Mirror Descent","created":"2022-02-22","cited_by_count":2,"area":null},{"id":"2211.15880","title":"Mirror descent of Hopfield model","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2411.11242","title":"Mirror Descent on Reproducing Kernel Banach Spaces","created":"2024-11-18","cited_by_count":2,"area":null},{"id":"2501.03289","title":"Adaptive Pruning of Pretrained Transformer via Differential Inclusions","created":"2025-01-06","cited_by_count":2,"area":null},{"id":"2208.08425","title":"SYNTHESIS: A Semi-Asynchronous Path-Integrated Stochastic Gradient Method for Distributed Learning in Computing Clusters","created":"2022-08-17","cited_by_count":1,"area":null},{"id":"2305.16424","title":"SketchOGD: Memory-Efficient Continual Learning","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2402.10474","title":"One-Bit Quantization and Sparsification for Multiclass Linear Classification with Strong Regularization","created":"2024-02-16","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":"2506.17187","title":"Optimal Implicit Bias in Linear Regression","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2602.18997","title":"Implicit Bias and Convergence of Matrix Stochastic Mirror Descent","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2210.15323","title":"Stochastic Mirror Descent in Average Ensemble Models","created":"2022-10-27","cited_by_count":0,"area":null},{"id":"2302.09433","title":"The Generalization Error of Stochastic Mirror Descent on Over-Parametrized Linear Models","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2304.10640","title":"Distributed Linear Solvers and Data Heterogeneity","created":"2023-04-20","cited_by_count":0,"area":null},{"id":"2510.16250","title":"One-Bit Quantization for Random Features Models","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2603.10485","title":"Dual Space Preconditioning for Gradient Descent in the Overparameterized Regime","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2605.07892","title":"Adaptive Regularization for Sparsity Control in Bregman-Based Optimizers","created":"2026-05-08","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}],"next_cursor":null}