{"total":243,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143,"area":null},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121,"area":null},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97,"area":null},{"id":"2202.14026","title":"Robust Training under Label Noise by Over-parameterization","created":"2022-02-28","cited_by_count":93,"area":null},{"id":"2210.15651","title":"Learning Single-Index Models with Shallow Neural Networks","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2407.08639","title":"$\\beta$-DPO: Direct Preference Optimization with Dynamic $\\beta$","created":"2024-07-11","cited_by_count":90,"area":"alignment"},{"id":"2110.02796","title":"An Unconstrained Layer-Peeled Perspective on Neural Collapse","created":"2021-10-06","cited_by_count":87,"area":null},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84,"area":null},{"id":"2106.15013","title":"Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction","created":"2021-06-28","cited_by_count":78,"area":null},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78,"area":null},{"id":"2206.04030","title":"High-dimensional limit theorems for SGD: Effective dynamics and critical scaling","created":"2022-06-08","cited_by_count":70,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2210.01513","title":"The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima","created":"2022-10-04","cited_by_count":51,"area":null},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50,"area":null},{"id":"2402.11867","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","created":"2024-02-19","cited_by_count":48,"area":null},{"id":"2402.01258","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","created":"2024-02-02","cited_by_count":46,"area":null},{"id":"2106.14289","title":"Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization","created":"2021-06-27","cited_by_count":45,"area":null},{"id":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44,"area":null},{"id":"2109.06141","title":"On Tilted Losses in Machine Learning: Theory and Applications","created":"2021-09-13","cited_by_count":43,"area":null},{"id":"2209.05045","title":"Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization","created":"2022-09-12","cited_by_count":43,"area":null},{"id":"2301.11500","title":"Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing","created":"2023-01-27","cited_by_count":42,"area":null},{"id":"2507.07101","title":"Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful","created":"2025-07-09","cited_by_count":41,"area":null},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35,"area":null},{"id":"2106.00198","title":"Gradient play in stochastic games: stationary points, convergence, and sample complexity","created":"2021-06-01","cited_by_count":34,"area":null},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2102.05274","title":"Stability of SGD: Tightness Analysis and Improved Bounds","created":"2021-02-10","cited_by_count":33,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2102.03198","title":"Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning","created":"2021-02-05","cited_by_count":31,"area":null},{"id":"2202.01331","title":"Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions","created":"2022-02-02","cited_by_count":31,"area":null},{"id":"2212.13827","title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","created":"2022-12-28","cited_by_count":28,"area":null},{"id":"2209.03525","title":"Implicit Full Waveform Inversion with Deep Neural Representation","created":"2022-09-08","cited_by_count":26,"area":null},{"id":"2106.02588","title":"Stochastic gradient descent with noise of machine learning type. Part II: Continuous time analysis","created":"2021-06-04","cited_by_count":25,"area":null},{"id":"2105.14417","title":"Overparameterization of deep ResNet: zero loss and mean-field analysis","created":"2021-05-30","cited_by_count":24,"area":null},{"id":"2107.13289","title":"The loss landscape of deep linear neural networks: a second-order analysis","created":"2021-07-28","cited_by_count":24,"area":null},{"id":"2207.03584","title":"Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling","created":"2022-07-07","cited_by_count":23,"area":null},{"id":"2301.08203","title":"An SDE for Modeling SAM: Theory and Insights","created":"2023-01-19","cited_by_count":22,"area":null},{"id":"1901.03674","title":"On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator","created":"2019-01-11","cited_by_count":21,"area":"offlinerl"},{"id":"2106.13792","title":"Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent","created":"2021-06-25","cited_by_count":21,"area":null},{"id":"2206.03345","title":"Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification","created":"2022-06-07","cited_by_count":21,"area":null},{"id":"2106.04975","title":"The dilemma of quantum neural networks","created":"2021-06-09","cited_by_count":20,"area":null},{"id":"2403.13249","title":"A Unified and General Framework for Continual Learning","created":"2024-03-20","cited_by_count":20,"area":null},{"id":"2502.09376","title":"LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)","created":"2025-02-13","cited_by_count":20,"area":null},{"id":"2202.03684","title":"Efficiently Escaping Saddle Points in Bilevel Optimization","created":"2022-02-08","cited_by_count":19,"area":null},{"id":"2306.14853","title":"Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles","created":"2023-06-26","cited_by_count":17,"area":null},{"id":"2101.04968","title":"Learning with Gradient Descent and Weakly Convex Losses","created":"2021-01-13","cited_by_count":16,"area":null},{"id":"2204.13751","title":"BEINIT: Avoiding Barren Plateaus in Variational Quantum Algorithms","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2102.02976","title":"Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels","created":"2021-02-05","cited_by_count":15,"area":null},{"id":"2103.04985","title":"Significance tests of feature relevance for a black-box learner","created":"2021-03-02","cited_by_count":15,"area":null},{"id":"2102.03803","title":"Lazy OCO: Online Convex Optimization on a Switching Budget","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2104.10095","title":"Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysis","created":"2021-04-20","cited_by_count":14,"area":null},{"id":"2107.04228","title":"Activated Gradients for Deep Neural Networks","created":"2021-07-09","cited_by_count":14,"area":null},{"id":"2310.15903","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2106.04769","title":"Submodular + Concave","created":"2021-06-09","cited_by_count":13,"area":null},{"id":"2207.01789","title":"Improved Global Guarantees for the Nonconvex Burer--Monteiro Factorization via Rank Overparameterization","created":"2022-07-05","cited_by_count":13,"area":null},{"id":"2211.15893","title":"Adap DP-FL: Differentially Private Federated Learning with Adaptive Noise","created":"2022-11-29","cited_by_count":13,"area":null},{"id":"2305.15659","title":"How to escape sharp minima with random perturbations","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2107.12780","title":"Physics-constrained Deep Learning for Robust Inverse ECG Modeling","created":"2021-07-26","cited_by_count":12,"area":null},{"id":"2108.00774","title":"A Random Matrix Perspective on Random Tensors","created":"2021-08-02","cited_by_count":12,"area":null},{"id":"2110.02926","title":"On the Global Convergence of Gradient Descent for multi-layer ResNets in the mean-field regime","created":"2021-10-06","cited_by_count":12,"area":null},{"id":"2110.04814","title":"Finding Second-Order Stationary Points in Nonconvex-Strongly-Concave Minimax Optimization","created":"2021-10-10","cited_by_count":12,"area":null},{"id":"2208.02711","title":"Agnostic Learning of General ReLU Activation Using Gradient Descent","created":"2022-08-04","cited_by_count":12,"area":null},{"id":"2302.09699","title":"Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks","created":"2023-02-20","cited_by_count":12,"area":null},{"id":"2305.06927","title":"Convergence of Alternating Gradient Descent for Matrix Factorization","created":"2023-05-11","cited_by_count":12,"area":null},{"id":"2309.10688","title":"On the different regimes of Stochastic Gradient Descent","created":"2023-09-19","cited_by_count":12,"area":null},{"id":"2504.09708","title":"Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization","created":"2025-04-13","cited_by_count":12,"area":null},{"id":"2111.14069","title":"Escape saddle points by a simple gradient-descent based algorithm","created":"2021-11-28","cited_by_count":11,"area":null},{"id":"2410.06441","title":"Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models","created":"2024-10-09","cited_by_count":11,"area":null},{"id":"2602.03067","title":"FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU","created":"2026-02-03","cited_by_count":11,"area":null},{"id":"2102.02969","title":"Sign-RIP: A Robust Restricted Isometry Property for Low-rank Matrix Recovery","created":"2021-02-05","cited_by_count":10,"area":null},{"id":"2108.04620","title":"A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10,"area":null},{"id":"2206.02041","title":"First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces","created":"2022-06-04","cited_by_count":10,"area":null},{"id":"2210.13767","title":"Networked Signal and Information Processing","created":"2022-10-25","cited_by_count":10,"area":null},{"id":"2212.07534","title":"Decentralized Nonconvex Optimization with Guaranteed Privacy and Accuracy","created":"2022-12-14","cited_by_count":10,"area":null},{"id":"2311.14056","title":"DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release","created":"2023-11-23","cited_by_count":10,"area":"safety"},{"id":"2104.00277","title":"A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions","created":"2021-04-01","cited_by_count":9,"area":null},{"id":"2112.07369","title":"Convergence proof for stochastic gradient descent in the training of deep neural networks with ReLU activation for constant target functions","created":"2021-12-13","cited_by_count":9,"area":null},{"id":"2208.07951","title":"On the generalization of learning algorithms that do not converge","created":"2022-08-16","cited_by_count":9,"area":null},{"id":"2209.14501","title":"On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2503.11514","title":"Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2602.18523","title":"The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure","created":"2026-02-19","cited_by_count":9,"area":null},{"id":"2103.13462","title":"Why Do Local Methods Solve Nonconvex Problems?","created":"2021-03-24","cited_by_count":8,"area":null},{"id":"2106.02985","title":"Escaping Saddle Points Faster with Stochastic Momentum","created":"2021-06-05","cited_by_count":8,"area":null},{"id":"2107.11774","title":"SGD with a Constant Large Learning Rate Can Converge to Local Maxima","created":"2021-07-25","cited_by_count":8,"area":null},{"id":"2303.13093","title":"Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent","created":"2023-03-23","cited_by_count":8,"area":null},{"id":"2311.02374","title":"Riemannian stochastic optimization methods avoid strict saddle points","created":"2023-11-04","cited_by_count":8,"area":null},{"id":"2504.14335","title":"Visual Prompting for One-shot Controllable Video Editing without Inversion","created":"2025-04-19","cited_by_count":8,"area":"diffusion"},{"id":"2102.06759","title":"Stochastic Gradient Langevin Dynamics with Variance Reduction","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2106.09815","title":"Escaping strict saddle points of the Moreau envelope in nonsmooth optimization","created":"2021-06-17","cited_by_count":7,"area":null},{"id":"2203.02790","title":"A Robust Spectral Algorithm for Overcomplete Tensor Decomposition","created":"2022-03-05","cited_by_count":7,"area":null},{"id":"2212.04025","title":"A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces","created":"2022-12-08","cited_by_count":7,"area":null},{"id":"2103.06875","title":"For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functions","created":"2021-03-11","cited_by_count":6,"area":null},{"id":"2111.05496","title":"ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees","created":"2021-11-10","cited_by_count":6,"area":null},{"id":"2210.01496","title":"Zeroth-Order Negative Curvature Finding: Escaping Saddle Points without Gradients","created":"2022-10-04","cited_by_count":6,"area":null},{"id":"2210.05782","title":"Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models","created":"2022-10-11","cited_by_count":6,"area":null},{"id":"2211.00915","title":"Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models","created":"2022-11-02","cited_by_count":6,"area":null},{"id":"2301.04733","title":"AGMN: Association Graph-based Graph Matching Network for Coronary Artery Semantic Labeling on Invasive Coronary Angiograms","created":"2023-01-11","cited_by_count":6,"area":null},{"id":"2310.06159","title":"Provably Accelerating Ill-Conditioned Low-rank Estimation via Scaled Gradient Descent, Even with Overparameterization","created":"2023-10-09","cited_by_count":6,"area":null}],"next_cursor":"100"}