{"total":41,"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":"2503.12645","title":"Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization","created":"2025-03-16","cited_by_count":92,"area":null},{"id":"2208.11195","title":"Robustness to Unbounded Smoothness of Generalized SignSGD","created":"2022-08-23","cited_by_count":81,"area":null},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77,"area":null},{"id":"2404.04454","title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization","created":"2024-04-05","cited_by_count":58,"area":null},{"id":"2403.13042","title":"TAPTR: Tracking Any Point with Transformers as Detection","created":"2024-03-19","cited_by_count":45,"area":null},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2305.07583","title":"MoMo: Momentum Models for Adaptive Learning Rates","created":"2023-05-12","cited_by_count":24,"area":null},{"id":"2505.19227","title":"Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf's Law","created":"2025-05-25","cited_by_count":24,"area":null},{"id":"2405.18199","title":"Adam with model exponential moving average is effective for nonconvex optimization","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2406.15244","title":"AdaGrad under Anisotropic Smoothness","created":"2024-06-21","cited_by_count":22,"area":null},{"id":"2506.02285","title":"Why Gradients Rapidly Increase Near the End of Training","created":"2025-06-02","cited_by_count":22,"area":null},{"id":"2407.16291","title":"TAPTRv2: Attention-based Position Update Improves Tracking Any Point","created":"2024-07-23","cited_by_count":18,"area":null},{"id":"2301.04935","title":"A Stochastic Proximal Polyak Step Size","created":"2023-01-12","cited_by_count":15,"area":null},{"id":"2311.04913","title":"An Improved Transformer-based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach","created":"2023-11-01","cited_by_count":12,"area":null},{"id":"2306.14062","title":"On the Uses of Large Language Models to Interpret Ambiguous Cyberattack Descriptions","created":"2023-06-24","cited_by_count":11,"area":null},{"id":"2401.09881","title":"GA-SmaAt-GNet: Generative Adversarial Small Attention GNet for Extreme Precipitation Nowcasting","created":"2024-01-18","cited_by_count":9,"area":null},{"id":"2402.13871","title":"An Explainable Transformer-based Model for Phishing Email Detection: A Large Language Model Approach","created":"2024-02-21","cited_by_count":9,"area":null},{"id":"2407.00928","title":"FoldGPT: Simple and Effective Large Language Model Compression Scheme","created":"2024-07-01","cited_by_count":9,"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":"2312.17369","title":"SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2502.02002","title":"The Ball-Proximal (=\"Broximal\") Point Method: a New Algorithm, Convergence Theory, and Applications","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2404.15289","title":"EEGDiR: Electroencephalogram denoising network for temporal information storage and global modeling through Retentive Network","created":"2024-03-20","cited_by_count":4,"area":null},{"id":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2405.08026","title":"ExplainableDetector: Exploring Transformer-based Language Modeling Approach for SMS Spam Detection with Explainability Analysis","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2412.02924","title":"Harnessing Loss Decomposition for Long-Horizon Wave Predictions via Deep Neural Networks","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2502.10650","title":"Generative Adversarial Networks for High-Dimensional Item Factor Analysis: A Deep Adversarial Learning Algorithm","created":"2025-02-15","cited_by_count":1,"area":null},{"id":"2509.19977","title":"Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2510.04988","title":"Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2512.07981","title":"CIP-Net: Continual Interpretable Prototype-based Network","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2605.04418","title":"Demystifying Manifold Constraints in LLM Pre-training","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2305.18324","title":"Regex-augmented Domain Transfer Topic Classification based on a Pre-trained Language Model: An application in Financial Domain","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2306.10278","title":"Adaptive Strategies in Non-convex Optimization","created":"2023-06-17","cited_by_count":0,"area":null},{"id":"2309.14662","title":"Transformer-based classification of user queries for medical consultancy with respect to expert specialization","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2409.06300","title":"An Attribute-Enriched Dataset and Auto-Annotated Pipeline for Open Detection","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2410.20428","title":"MedGo: A Chinese Medical Large Language Model","created":"2024-10-27","cited_by_count":0,"area":null},{"id":"2504.20552","title":"BrAIcht, a theatrical agent that speaks like Bertolt Brecht's characters","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2506.06054","title":"FPDANet: A Multi-Section Classification Model for Intelligent Screening of Fetal Ultrasound","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2507.15303","title":"Universal crystal material property prediction via multi-view geometric fusion in graph transformers","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2601.09207","title":"Point Tracking as a Temporal Cue for Robust Myocardial Segmentation in Echocardiography Videos","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2609.40170","title":"MANET-GNN: Learned Decentralized Optimization of Power Allocation in Multi-Channel MANETs","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}