{"total":198,"rows":[{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50,"area":null},{"id":"2110.04840","title":"Heavy Ball Neural Ordinary Differential Equations","created":"2021-10-10","cited_by_count":42,"area":null},{"id":"2102.04396","title":"SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality","created":"2021-02-08","cited_by_count":35,"area":null},{"id":"2107.06608","title":"Continuous vs. Discrete Optimization of Deep Neural Networks","created":"2021-07-14","cited_by_count":34,"area":null},{"id":"2105.08158","title":"The Confluence of Networks, Games and Learning","created":"2021-05-17","cited_by_count":26,"area":null},{"id":"2202.12482","title":"Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsity","created":"2022-02-25","cited_by_count":25,"area":null},{"id":"2110.03891","title":"Does Momentum Change the Implicit Regularization on Separable Data?","created":"2021-10-08","cited_by_count":22,"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":"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":"2104.05508","title":"Noether: The More Things Change, the More Stay the Same","created":"2021-04-12","cited_by_count":19,"area":null},{"id":"2101.12051","title":"Edge Federated Learning Via Unit-Modulus Over-The-Air Computation","created":"2021-01-28","cited_by_count":16,"area":null},{"id":"2106.07644","title":"A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2105.13922","title":"Discretization Drift in Two-Player Games","created":"2021-05-28","cited_by_count":14,"area":null},{"id":"2103.01338","title":"Acceleration via Fractal Learning Rate Schedules","created":"2021-03-01","cited_by_count":13,"area":null},{"id":"2107.08225","title":"On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2210.15898","title":"Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis","created":"2022-10-28","cited_by_count":13,"area":null},{"id":"2305.14076","title":"Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent","created":"2023-05-23","cited_by_count":13,"area":null},{"id":"2203.01443","title":"Continuous-Time Meta-Learning with Forward Mode Differentiation","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2301.00008","title":"Effects of Data Geometry in Early Deep Learning","created":"2022-12-29","cited_by_count":12,"area":null},{"id":"2205.14173","title":"Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport","created":"2022-05-27","cited_by_count":11,"area":null},{"id":"2405.12888","title":"Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows","created":"2024-05-21","cited_by_count":11,"area":null},{"id":"2110.07034","title":"How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies","created":"2021-10-13","cited_by_count":10,"area":null},{"id":"2112.09579","title":"Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems","created":"2021-12-17","cited_by_count":10,"area":null},{"id":"2202.11104","title":"A duality connecting neural network and cosmological dynamics","created":"2022-02-22","cited_by_count":10,"area":null},{"id":"2302.11147","title":"Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning","created":"2023-02-22","cited_by_count":10,"area":null},{"id":"2310.04006","title":"Accelerating optimization over the space of probability measures","created":"2023-10-06","cited_by_count":10,"area":null},{"id":"2604.14108","title":"Momentum Further Constrains Sharpness at the Edge of Stochastic Stability","created":"2026-04-15","cited_by_count":10,"area":null},{"id":"2103.11333","title":"ANITA: An Optimal Loopless Accelerated Variance-Reduced Gradient Method","created":"2021-03-21","cited_by_count":9,"area":null},{"id":"2108.03947","title":"On the Hyperparameters in Stochastic Gradient Descent with Momentum","created":"2021-08-09","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":"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":"2112.13826","title":"Last-Iterate Convergence of Saddle-Point Optimizers via High-Resolution Differential Equations","created":"2021-12-27","cited_by_count":8,"area":null},{"id":"2209.08862","title":"Gradient Norm Minimization of Nesterov Acceleration: $o(1/k^3)$","created":"2022-09-19","cited_by_count":8,"area":null},{"id":"2211.12386","title":"A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms","created":"2022-11-22","cited_by_count":8,"area":null},{"id":"2602.22681","title":"Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2107.01832","title":"Provable Convergence of Nesterov's Accelerated Gradient Method for Over-Parameterized Neural Networks","created":"2021-07-05","cited_by_count":7,"area":null},{"id":"2111.06171","title":"Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum","created":"2021-11-11","cited_by_count":7,"area":null},{"id":"2303.01471","title":"Quantum Hamiltonian Descent","created":"2023-03-02","cited_by_count":7,"area":null},{"id":"2311.15587","title":"Quantum Langevin Dynamics for Optimization","created":"2023-11-27","cited_by_count":7,"area":null},{"id":"2410.08395","title":"Nesterov acceleration in benignly non-convex landscapes","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2411.09734","title":"Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations","created":"2024-11-14","cited_by_count":7,"area":null},{"id":"2102.11537","title":"Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization","created":"2021-02-23","cited_by_count":6,"area":null},{"id":"2205.12442","title":"Lyapunov function approach for approximation algorithm design and analysis: with applications in submodular maximization","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2211.01610","title":"Proximal Subgradient Norm Minimization of ISTA and FISTA","created":"2022-11-03","cited_by_count":6,"area":null},{"id":"2302.07851","title":"Continuized Acceleration for Quasar Convex Functions in Non-Convex Optimization","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2503.23462","title":"Accelerated Stein Variational Gradient Flow","created":"2025-03-30","cited_by_count":6,"area":null},{"id":"2102.11755","title":"Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems","created":"2021-02-23","cited_by_count":5,"area":null},{"id":"2203.10592","title":"Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents","created":"2022-03-20","cited_by_count":5,"area":null},{"id":"2208.06619","title":"Riemannian accelerated gradient methods via extrapolation","created":"2022-08-13","cited_by_count":5,"area":null},{"id":"2210.06705","title":"From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2302.00316","title":"Accelerated First-Order Optimization under Nonlinear Constraints","created":"2023-02-01","cited_by_count":5,"area":null},{"id":"2303.17192","title":"Sublinear Convergence Rates of Extragradient-Type Methods: A Survey on Classical and Recent Developments","created":"2023-03-30","cited_by_count":5,"area":null},{"id":"2307.02719","title":"Understanding Uncertainty Sampling via Equivalent Loss","created":"2023-07-06","cited_by_count":5,"area":null},{"id":"2412.15554","title":"Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation","created":"2024-12-20","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":"2101.12101","title":"Potential Function-based Framework for Making the Gradients Small in Convex and Min-Max Optimization","created":"2021-01-28","cited_by_count":4,"area":null},{"id":"2211.14645","title":"Accelerated Riemannian Optimization: Handling Constraints with a Prox to Bound Geometric Penalties","created":"2022-11-26","cited_by_count":4,"area":null},{"id":"2301.07902","title":"A Nonstochastic Control Approach to Optimization","created":"2023-01-19","cited_by_count":4,"area":null},{"id":"2403.13704","title":"Improving the Adaptive Moment Estimation (ADAM) stochastic optimizer through an Implicit-Explicit (IMEX) time-stepping approach","created":"2024-03-20","cited_by_count":4,"area":null},{"id":"2506.00181","title":"On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2602.16167","title":"Muon with Spectral Guidance: Efficient Optimization for Scientific Machine Learning","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2105.06577","title":"Online Algorithms and Policies Using Adaptive and Machine Learning Approaches","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2105.08832","title":"A Contraction Theory Approach to Optimization Algorithms from Acceleration Flows","created":"2021-05-18","cited_by_count":3,"area":null},{"id":"2112.01363","title":"Breaking the Convergence Barrier: Optimization via Fixed-Time Convergent Flows","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2202.06152","title":"Analysis of Dual-Based PID Controllers through Convolutional Mirror Descent","created":"2022-02-12","cited_by_count":3,"area":null},{"id":"2207.06066","title":"AdamNODEs: When Neural ODE Meets Adaptive Moment Estimation","created":"2022-07-13","cited_by_count":3,"area":null},{"id":"2210.06819","title":"Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2210.14488","title":"History-Based, Bayesian, Closure for Stochastic Parameterization: Application to Lorenz '96","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2303.17805","title":"On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks","created":"2023-03-31","cited_by_count":3,"area":null},{"id":"2304.02883","title":"GA-HQS: MRI reconstruction via a generically accelerated unfolding approach","created":"2023-04-06","cited_by_count":3,"area":null},{"id":"2310.01145","title":"Parallel-in-Time Probabilistic Numerical ODE Solvers","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2310.17610","title":"A qualitative difference between gradient flows of convex functions in finite- and infinite-dimensional Hilbert spaces","created":"2023-10-26","cited_by_count":3,"area":null},{"id":"2405.10618","title":"Distributed Event-Based Learning via ADMM","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2410.16849","title":"Polyak's Heavy Ball Method Achieves Accelerated Local Rate of Convergence under Polyak-Lojasiewicz Inequality","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2412.00864","title":"Explicit and data-Efficient Encoding via Gradient Flow","created":"2024-12-01","cited_by_count":3,"area":null},{"id":"2505.19171","title":"Computational Inertia as a Conserved Quantity in Frictionless and Damped Learning Dynamics","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2505.19537","title":"Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2507.03404","title":"On the Effectiveness of the z-Transform Method in Quadratic Optimization","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2602.00334","title":"Adaptive Momentum and Nonlinear Damping for Neural Network Training","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2101.01505","title":"Delayed Projection Techniques for Linearly Constrained Problems: Convergence Rates, Acceleration, and Applications","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2111.04596","title":"Inertial Newton Algorithms Avoiding Strict Saddle Points","created":"2021-11-08","cited_by_count":2,"area":null},{"id":"2209.03705","title":"Losing momentum in continuous-time stochastic optimisation","created":"2022-09-08","cited_by_count":2,"area":null},{"id":"2209.14937","title":"NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2210.07513","title":"Continuous-in-time Limit for Bayesian Bandits","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2212.03320","title":"Reinforcement Learning for Molecular Dynamics Optimization: A Stochastic Pontryagin Maximum Principle Approach","created":"2022-12-06","cited_by_count":2,"area":null},{"id":"2212.06319","title":"Linear Convergence of ISTA and FISTA","created":"2022-12-13","cited_by_count":2,"area":null},{"id":"2301.02268","title":"Restarts subject to approximate sharpness: A parameter-free and optimal scheme for first-order methods","created":"2023-01-05","cited_by_count":2,"area":null},{"id":"2303.04328","title":"The Novel Adaptive Fractional Order Gradient Decent Algorithms Design via Robust Control","created":"2023-03-08","cited_by_count":2,"area":null},{"id":"2303.16241","title":"Convergence of the Stochastic Heavy Ball Method With Approximate Gradients and/or Block Updating","created":"2023-03-28","cited_by_count":2,"area":null},{"id":"2305.08658","title":"On the connections between optimization algorithms, Lyapunov functions, and differential equations: theory and insights","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2311.02002","title":"A Variational Perspective on High-Resolution ODEs","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2312.06547","title":"KF-PLS: Optimizing Kernel Partial Least-Squares (K-PLS) with Kernel Flows","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2402.01036","title":"Fisher information dissipation for time inhomogeneous stochastic differential equations","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2407.20620","title":"Accelerated forward-backward and Douglas-Rachford splitting dynamics","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2411.06278","title":"A Natural Primal-Dual Hybrid Gradient Method for Adversarial Neural Network Training on Solving Partial Differential Equations","created":"2024-11-09","cited_by_count":2,"area":null},{"id":"2412.20365","title":"Accelerated regularized learning in finite N-person games","created":"2024-12-29","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":"2503.00509","title":"Functional multi-armed bandit and the best function identification problems","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2505.12599","title":"Accelerated Markov Chain Monte Carlo Algorithms on Discrete States","created":"2025-05-19","cited_by_count":2,"area":null}],"next_cursor":"100"}