{"total":120,"rows":[{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172,"area":null},{"id":"2207.14484","title":"Adaptive Gradient Methods at the Edge of Stability","created":"2022-07-29","cited_by_count":101,"area":null},{"id":"2206.08213","title":"A Closer Look at Smoothness in Domain Adversarial Training","created":"2022-06-16","cited_by_count":85,"area":null},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49,"area":null},{"id":"2306.04815","title":"Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning","created":"2023-06-07","cited_by_count":31,"area":null},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27,"area":null},{"id":"2109.05109","title":"Toward Communication Efficient Adaptive Gradient Method","created":"2021-09-10","cited_by_count":25,"area":null},{"id":"2205.14375","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","created":"2022-05-28","cited_by_count":19,"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":"2105.13937","title":"Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks","created":"2021-05-28","cited_by_count":11,"area":null},{"id":"2107.07572","title":"Globally Convergent Multilevel Training of Deep Residual Networks","created":"2021-07-15","cited_by_count":11,"area":null},{"id":"2410.19964","title":"Understanding Adam Requires Better Rotation Dependent Assumptions","created":"2024-10-25","cited_by_count":11,"area":null},{"id":"2205.11016","title":"MolMiner: You only look once for chemical structure recognition","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2307.00430","title":"WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution","created":"2023-07-01","cited_by_count":10,"area":null},{"id":"2407.14340","title":"Large Kernel Distillation Network for Efficient Single Image Super-Resolution","created":"2024-07-19","cited_by_count":9,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2110.09057","title":"Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization","created":"2021-10-18","cited_by_count":8,"area":null},{"id":"2302.11085","title":"Learning to Generalize Provably in Learning to Optimize","created":"2023-02-22","cited_by_count":8,"area":null},{"id":"2407.20209","title":"Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning","created":"2024-07-29","cited_by_count":8,"area":null},{"id":"2102.07927","title":"Structured Dropout Variational Inference for Bayesian Neural Networks","created":"2021-02-16","cited_by_count":7,"area":null},{"id":"2307.15424","title":"Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesis","created":"2023-07-28","cited_by_count":7,"area":null},{"id":"2409.04707","title":"Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training","created":"2024-09-07","cited_by_count":7,"area":null},{"id":"2106.11514","title":"Rethinking Adam: A Twofold Exponential Moving Average Approach","created":"2021-06-22","cited_by_count":6,"area":null},{"id":"2201.09209","title":"Weight Expansion: A New Perspective on Dropout and Generalization","created":"2022-01-23","cited_by_count":6,"area":null},{"id":"2307.00631","title":"Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers","created":"2023-07-02","cited_by_count":6,"area":null},{"id":"2406.00446","title":"Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2511.21622","title":"On the Origin of Algorithmic Progress in AI","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2102.09804","title":"Local Convergence of Adaptive Gradient Descent Optimizers","created":"2021-02-19","cited_by_count":5,"area":null},{"id":"2105.05155","title":"TAG: Task-based Accumulated Gradients for Lifelong learning","created":"2021-05-11","cited_by_count":5,"area":null},{"id":"2201.10271","title":"Convolutional Xformers for Vision","created":"2022-01-25","cited_by_count":5,"area":null},{"id":"2210.16400","title":"Flatter, faster: scaling momentum for optimal speedup of SGD","created":"2022-10-28","cited_by_count":5,"area":null},{"id":"2310.08858","title":"Adam-family Methods with Decoupled Weight Decay in Deep Learning","created":"2023-10-13","cited_by_count":5,"area":null},{"id":"2406.16633","title":"MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2407.05638","title":"HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion","created":"2024-07-08","cited_by_count":5,"area":null},{"id":"2108.13297","title":"VTLayout: Fusion of Visual and Text Features for Document Layout Analysis","created":"2021-08-12","cited_by_count":4,"area":null},{"id":"2202.04509","title":"Optimal learning rate schedules in high-dimensional non-convex optimization problems","created":"2022-02-09","cited_by_count":4,"area":null},{"id":"2312.01658","title":"AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix","created":"2023-12-04","cited_by_count":4,"area":null},{"id":"2410.21346","title":"Towards Trustworthy Machine Learning in Production: An Overview of the Robustness in MLOps Approach","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2503.13145","title":"High-entropy Advantage in Neural Networks' Generalizability","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2605.31371","title":"Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2103.14689","title":"Exploiting Adam-like Optimization Algorithms to Improve the Performance of Convolutional Neural Networks","created":"2021-03-26","cited_by_count":3,"area":null},{"id":"2104.03418","title":"Quantum Enhanced Filter: QFilter","created":"2021-04-07","cited_by_count":3,"area":null},{"id":"2203.12191","title":"An Adaptive Gradient Method with Energy and Momentum","created":"2022-03-23","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2103.01400","title":"Smoothness Analysis of Adversarial Training","created":"2021-03-02","cited_by_count":2,"area":null},{"id":"2105.04356","title":"Coconut trees detection and segmentation in aerial imagery using mask region-based convolution neural network","created":"2021-05-10","cited_by_count":2,"area":null},{"id":"2207.01847","title":"PoF: Post-Training of Feature Extractor for Improving Generalization","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2302.05516","title":"Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize","created":"2023-02-10","cited_by_count":2,"area":null},{"id":"2307.00407","title":"WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting","created":"2023-07-01","cited_by_count":2,"area":null},{"id":"2312.01232","title":"A Comprehensive Study of Vision Transformers in Image Classification Tasks","created":"2023-12-02","cited_by_count":2,"area":null},{"id":"2401.10962","title":"One Step Learning, One Step Review","created":"2024-01-19","cited_by_count":2,"area":null},{"id":"2412.11074","title":"Adapter-Enhanced Semantic Prompting for Continual Learning","created":"2024-12-15","cited_by_count":2,"area":null},{"id":"2412.12473","title":"A Method for Enhancing Generalization of Adam by Multiple Integrations","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2503.17072","title":"Multi-Span Optical Power Spectrum Evolution Modeling using ML-based Multi-Decoder Attention Framework","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2511.13465","title":"AdamNX: An Adam improvement algorithm based on a novel exponential decay mechanism for the second-order moment estimate","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2605.17787","title":"Revisiting the Adam-SGD Gap in LLM Pre-Training: The Role of Large Effective Learning Rates","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.19811","title":"LionMuon: Alternating Spectral and Sign Descent for Efficient Training","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2606.21514","title":"Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective","created":"2026-06-19","cited_by_count":2,"area":null},{"id":"2103.00147","title":"Statistical Measures For Defining Curriculum Scoring Function","created":"2021-02-27","cited_by_count":1,"area":null},{"id":"2106.06749","title":"A decreasing scaling transition scheme from Adam to SGD","created":"2021-06-12","cited_by_count":1,"area":null},{"id":"2112.11619","title":"A Convergent ADMM Framework for Efficient Neural Network Training","created":"2021-12-22","cited_by_count":1,"area":null},{"id":"2205.10386","title":"A Dynamic Weighted Tabular Method for Convolutional Neural Networks","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2308.00177","title":"Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity","created":"2023-07-31","cited_by_count":1,"area":null},{"id":"2311.02818","title":"Signal Processing Meets SGD: From Momentum to Filter","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2312.15295","title":"AdamL: A fast adaptive gradient method incorporating loss function","created":"2023-12-23","cited_by_count":1,"area":null},{"id":"2401.09622","title":"Is Hyper-Parameter Optimization Different for Software Analytics?","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2401.11408","title":"SEBERTNets: Sequence Enhanced BERT Networks for Event Entity Extraction Tasks Oriented to the Finance Field","created":"2024-01-21","cited_by_count":1,"area":null},{"id":"2402.14949","title":"Enhancing Power Quality Event Classification with AI Transformer Models","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2407.19259","title":"Fine-Grained Scene Graph Generation via Sample-Level Bias Prediction","created":"2024-07-27","cited_by_count":1,"area":null},{"id":"2506.06815","title":"Path Integral Optimiser: Global Optimisation via Neural Schr\\\"odinger-F\\\"ollmer Diffusion","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2512.01881","title":"Unifying Sign and Magnitude for Optimizing Deep Vision Networks via ThermoLion","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2603.02649","title":"HomeAdam: Adam and AdamW Algorithms Sometimes Go Home to Obtain Better Provable Generalization","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.06120","title":"Dynamic Momentum Recalibration in Online Gradient Learning","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.06613","title":"OptiRoulette Optimizer: A New Stochastic Meta-Optimizer for up to 5.3x Faster Convergence","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2603.10079","title":"Large Spikes in Stochastic Gradient Descent: A Large-Deviations View","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2606.06418","title":"Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2101.10037","title":"Optimizing Convergence for Iterative Learning of ARIMA for Stationary Time Series","created":"2021-01-25","cited_by_count":0,"area":null},{"id":"2102.01006","title":"Dosimetric impact of physician style variations in contouring CTV for post-operative prostate cancer: A deep learning-based simulation study","created":"2021-02-01","cited_by_count":0,"area":null},{"id":"2102.10296","title":"Versatile and Robust Transient Stability Assessment via Instance Transfer Learning","created":"2021-02-20","cited_by_count":0,"area":null},{"id":"2102.13653","title":"On the Generalization of Stochastic Gradient Descent with Momentum","created":"2021-02-26","cited_by_count":0,"area":null},{"id":"2104.04197","title":"BERT-based Chinese Text Classification for Emergency Domain with a Novel Loss Function","created":"2021-04-09","cited_by_count":0,"area":null},{"id":"2107.08849","title":"Exploring the efficacy of neural networks for trajectory compression and the inverse problem","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2302.09376","title":"Why is parameter averaging beneficial in SGD? An objective smoothing perspective","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2303.03540","title":"Judging Adam: Studying the Performance of Optimization Methods on ML4SE Tasks","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2303.15464","title":"Mathematical Challenges in Deep Learning","created":"2023-03-24","cited_by_count":0,"area":null},{"id":"2305.13664","title":"Layer-wise Adaptive Step-Sizes for Stochastic First-Order Methods for Deep Learning","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2306.01423","title":"Break a Lag: Triple Exponential Moving Average for Enhanced Optimization","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2306.14039","title":"Semantic Segmentation of Porosity in 4D Spatio-Temporal X-ray \\mu CT of Titanium Coated Ni wires using Deep Learning","created":"2023-06-24","cited_by_count":0,"area":null},{"id":"2308.10740","title":"We Don't Need No Adam, All We Need Is EVE: On The Variance of Dual Learning Rate And Beyond","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2309.02130","title":"Asymmetric Momentum: A Rethinking of Gradient Descent","created":"2023-09-05","cited_by_count":0,"area":null},{"id":"2310.12298","title":"Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2310.20574","title":"Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2312.10024","title":"Accelerating Neural Network Training: A Brief Review","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2402.15262","title":"Dynamic Memory Based Adaptive Optimization","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2404.06549","title":"Variational Stochastic Gradient Descent for Deep Neural Networks","created":"2024-04-09","cited_by_count":0,"area":null},{"id":"2409.10582","title":"WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2410.06171","title":"Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2410.19781","title":"Feasibility Analysis of Federated Neural Networks for Explainable Detection of Atrial Fibrillation","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2411.16295","title":"A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roads","created":"2024-11-25","cited_by_count":0,"area":null}],"next_cursor":"100"}