{"total":66,"rows":[{"id":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2101.09612","title":"On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths","created":"2021-01-24","cited_by_count":44,"area":null},{"id":"2408.10147","title":"In-Context Learning with Representations: Contextual Generalization of Trained Transformers","created":"2024-08-19","cited_by_count":38,"area":null},{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37,"area":null},{"id":"2205.10217","title":"Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization","created":"2022-05-20","cited_by_count":36,"area":null},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31,"area":null},{"id":"2111.01875","title":"Subquadratic Overparameterization for Shallow Neural Networks","created":"2021-11-02","cited_by_count":26,"area":null},{"id":"2112.08297","title":"Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime","created":"2021-12-15","cited_by_count":26,"area":null},{"id":"2211.07844","title":"Characterizing the Spectrum of the NTK via a Power Series Expansion","created":"2022-11-15","cited_by_count":22,"area":null},{"id":"2109.09304","title":"Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks","created":"2021-09-20","cited_by_count":21,"area":null},{"id":"2309.01213","title":"Implicit regularization of deep residual networks towards neural ODEs","created":"2023-09-03","cited_by_count":20,"area":null},{"id":"2110.05645","title":"A global convergence theory for deep ReLU implicit networks via over-parameterization","created":"2021-10-11","cited_by_count":17,"area":null},{"id":"2410.04887","title":"Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2209.07238","title":"Generalization Properties of NAS under Activation and Skip Connection Search","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2310.10767","title":"Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2311.01575","title":"On the Convergence of Encoder-only Shallow Transformers","created":"2023-11-02","cited_by_count":13,"area":null},{"id":"2405.14630","title":"Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2102.09671","title":"When Are Solutions Connected in Deep Networks?","created":"2021-02-18","cited_by_count":11,"area":null},{"id":"2206.02927","title":"Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime","created":"2022-06-06","cited_by_count":11,"area":null},{"id":"2305.12100","title":"How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features","created":"2023-05-20","cited_by_count":11,"area":null},{"id":"2411.07538","title":"Unraveling the Gradient Descent Dynamics of Transformers","created":"2024-11-12","cited_by_count":11,"area":null},{"id":"2107.10868","title":"Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time","created":"2021-07-22","cited_by_count":10,"area":null},{"id":"2205.13814","title":"Global Convergence of Over-parameterized Deep Equilibrium Models","created":"2022-05-27","cited_by_count":10,"area":null},{"id":"2201.04738","title":"Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks","created":"2022-01-12","cited_by_count":9,"area":null},{"id":"2101.07150","title":"Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples","created":"2021-01-18","cited_by_count":8,"area":null},{"id":"2209.08399","title":"Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$","created":"2022-09-17","cited_by_count":7,"area":null},{"id":"2209.15106","title":"Restricted Strong Convexity of Deep Learning Models with Smooth Activations","created":"2022-09-29","cited_by_count":7,"area":null},{"id":"2210.05371","title":"On skip connections and normalisation layers in deep optimisation","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2211.06077","title":"Overparameterized random feature regression with nearly orthogonal data","created":"2022-11-11","cited_by_count":7,"area":null},{"id":"2403.13134","title":"Robust NAS under adversarial training: benchmark, theory, and beyond","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2506.05249","title":"On the Convergence of Gradient Descent on Learning Transformers with Residual Connections","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2205.07463","title":"Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths","created":"2022-05-16","cited_by_count":5,"area":null},{"id":"2209.13394","title":"Magnitude and Angle Dynamics in Training Single ReLU Neurons","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2211.04589","title":"Finite Sample Identification of Wide Shallow Neural Networks with Biases","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2306.05850","title":"Deterministic equivalent of the Conjugate Kernel matrix associated to Artificial Neural Networks","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2407.12354","title":"Invertible Neural Warp for NeRF","created":"2024-07-17","cited_by_count":5,"area":null},{"id":"2301.09511","title":"On the Convergence of the Gradient Descent Method with Stochastic Fixed-point Rounding Errors under the Polyak-Lojasiewicz Inequality","created":"2023-01-23","cited_by_count":4,"area":null},{"id":"2303.05728","title":"On the effectiveness of neural priors in modeling dynamical systems","created":"2023-03-10","cited_by_count":4,"area":null},{"id":"2405.01680","title":"Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2505.11664","title":"A Local Polyak-Lojasiewicz and Descent Lemma of Gradient Descent For Overparametrized Linear Models","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2509.20829","title":"Explaining Grokking and Information Bottleneck through Neural Collapse Emergence","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2510.17506","title":"Convergence Rates for Gradient Descent on the Edge of Stability in Overparametrised Least Squares","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2511.03892","title":"A general technique for approximating high-dimensional empirical kernel matrices","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2402.04783","title":"Analyzing the Neural Tangent Kernel of Periodically Activated Coordinate Networks","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2403.09889","title":"Generalization of Scaled Deep ResNets in the Mean-Field Regime","created":"2024-03-14","cited_by_count":3,"area":null},{"id":"2509.22214","title":"A Law of Data Reconstruction for Random Features (and Beyond)","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2104.02388","title":"Generalization of GANs and overparameterized models under Lipschitz continuity","created":"2021-04-06","cited_by_count":2,"area":null},{"id":"2202.03524","title":"Finite-Sum Optimization: A New Perspective for Convergence to a Global Solution","created":"2022-02-07","cited_by_count":2,"area":null},{"id":"2205.13507","title":"A Framework for Overparameterized Learning","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2309.04860","title":"Approximation Results for Gradient Descent trained Neural Networks","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2507.06367","title":"The Riemannian Geometry Associated to Gradient Flows of Linear Convolutional Networks","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.01943","title":"Smooth Quasar-Convex Optimization with Constraints","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2102.09030","title":"Proactive DP: A Multple Target Optimization Framework for DP-SGD","created":"2021-02-17","cited_by_count":1,"area":null},{"id":"2111.05478","title":"SGD Through the Lens of Kolmogorov Complexity","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2405.11451","title":"Error Analysis of Three-Layer Neural Network Trained with PGD for Deep Ritz Method","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2405.11696","title":"Approximation and Gradient Descent Training with Neural Networks","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2604.10373","title":"Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2607.08380","title":"Dynamics of Gradient Descent with Large Step Size Near a Manifold of Flat Minima","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2112.14011","title":"To Supervise or Not: How to Effectively Learn Wireless Interference Management Models?","created":"2021-12-28","cited_by_count":0,"area":null},{"id":"2206.03254","title":"Demystifying the Global Convergence Puzzle of Learning Over-parameterized ReLU Nets in Very High Dimensions","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2402.02711","title":"Architectural Strategies for the optimization of Physics-Informed Neural Networks","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2410.10887","title":"ActNAS : Generating Efficient YOLO Models using Activation NAS","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2501.18092","title":"Learning Provably Improves the Convergence of Gradient Descent","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2509.23887","title":"Gradient Flow Convergence Guarantee for General Neural Network Architectures","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2605.25275","title":"Label-NTK Alignments and A Tighter Convergence Bound in the NTK Regime","created":"2026-05-24","cited_by_count":0,"area":null}],"next_cursor":null}