{"list":"other","total":136,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"2509.01440","title":"Benchmarking Optimizers for Large Language Model Pretraining","created":"2025-09-01","cited_by_count":68},{"id":"2507.11005","title":"AdaMuon: Adaptive Muon Optimizer","created":"2025-07-15","cited_by_count":67},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57},{"id":"2402.15751","title":"Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning","created":"2024-02-24","cited_by_count":54},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47},{"id":"2206.13033","title":"Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization","created":"2022-06-27","cited_by_count":36},{"id":"2310.10195","title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate","created":"2023-10-16","cited_by_count":31},{"id":"2601.08393","title":"Controlled LLM Training on Spectral Sphere","created":"2026-01-13","cited_by_count":31},{"id":"2410.08989","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","created":"2024-10-11","cited_by_count":26},{"id":"1910.09126","title":"Communication-Efficient Local Decentralized SGD Methods","created":"2019-10-21","cited_by_count":23},{"id":"2002.04839","title":"LaProp: Separating Momentum and Adaptivity in Adam","created":"2020-02-12","cited_by_count":20},{"id":"2006.02409","title":"On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs","created":"2020-06-03","cited_by_count":19},{"id":"2505.24749","title":"SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training","created":"2025-05-30","cited_by_count":19},{"id":"2011.11985","title":"Adam$^+$: A Stochastic Method with Adaptive Variance Reduction","created":"2020-11-24","cited_by_count":18},{"id":"2405.12807","title":"FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information","created":"2024-05-21","cited_by_count":18},{"id":"2502.03304","title":"Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning","created":"2025-02-05","cited_by_count":18},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18},{"id":"2510.27403","title":"FedMuon: Accelerating Federated Learning with Matrix Orthogonalization","created":"2025-10-31","cited_by_count":16},{"id":"2511.20626","title":"ROOT: Robust Orthogonalized Optimizer for Neural Network Training","created":"2025-11-25","cited_by_count":15},{"id":"2401.12033","title":"Momentum-SAM: Sharpness Aware Minimization without Computational Overhead","created":"2024-01-22","cited_by_count":14},{"id":"2506.09034","title":"FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed","created":"2025-06-10","cited_by_count":14},{"id":"2602.17080","title":"Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum","created":"2026-02-19","cited_by_count":14},{"id":"2502.12346","title":"QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models","created":"2025-02-17","cited_by_count":11},{"id":"2011.02150","title":"EAdam Optimizer: How $\\epsilon$ Impact Adam","created":"2020-11-04","cited_by_count":10},{"id":"1905.11286","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","created":"2019-05-27","cited_by_count":9},{"id":"2105.10190","title":"AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks","created":"2021-05-21","cited_by_count":9},{"id":"2410.09823","title":"Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models","created":"2024-10-13","cited_by_count":9},{"id":"2411.10696","title":"HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization","created":"2024-11-16","cited_by_count":9},{"id":"2502.07752","title":"Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension","created":"2025-02-11","cited_by_count":9},{"id":"2006.16541","title":"AdaSGD: Bridging the gap between SGD and Adam","created":"2020-06-30","cited_by_count":8},{"id":"2403.14958","title":"Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices","created":"2024-03-22","cited_by_count":8},{"id":"2412.11768","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","created":"2024-12-16","cited_by_count":8},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8},{"id":"2006.06587","title":"AdaS: Adaptive Scheduling of Stochastic Gradients","created":"2020-06-11","cited_by_count":7},{"id":"2210.11693","title":"Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale","created":"2022-10-21","cited_by_count":7},{"id":"2008.11343","title":"APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD Algorithm","created":"2020-08-26","cited_by_count":6},{"id":"2502.11034","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping","created":"2025-02-16","cited_by_count":6},{"id":"2503.12668","title":"ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory","created":"2025-03-16","cited_by_count":6},{"id":"2505.13430","title":"Fine-tuning Quantized Neural Networks with Zeroth-order Optimization","created":"2025-05-19","cited_by_count":6},{"id":"2505.16363","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","created":"2025-05-22","cited_by_count":6},{"id":"2003.12705","title":"Differentially Private Federated Learning for Resource-Constrained Internet of Things","created":"2020-03-28","cited_by_count":5},{"id":"2008.08445","title":"Domain-specific Communication Optimization for Distributed DNN Training","created":"2020-08-16","cited_by_count":5},{"id":"2302.01068","title":"FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations","created":"2023-02-02","cited_by_count":5},{"id":"2501.04287","title":"ElasticZO: A Memory-Efficient On-Device Learning with Combined Zeroth- and First-Order Optimization","created":"2025-01-08","cited_by_count":5},{"id":"2502.07488","title":"Improving Adaptive Moment Optimization via Preconditioner Diagonalization","created":"2025-02-11","cited_by_count":5},{"id":"2502.19571","title":"LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM","created":"2025-02-26","cited_by_count":5},{"id":"2505.18886","title":"KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning","created":"2025-05-24","cited_by_count":5},{"id":"2507.09823","title":"Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization","created":"2025-07-13","cited_by_count":5},{"id":"2601.02523","title":"First Provably Optimal Asynchronous SGD for Homogeneous and Heterogeneous Data","created":"2026-01-05","cited_by_count":5},{"id":"2602.23349","title":"FlashOptim: Optimizers for Memory-Efficient Training","created":"2026-02-26","cited_by_count":5},{"id":"2501.13516","title":"Communication-Efficient Stochastic Distributed Learning","created":"2025-01-23","cited_by_count":4},{"id":"2502.11513","title":"MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models","created":"2025-02-17","cited_by_count":4},{"id":"2503.08427","title":"Accelerated Distributed Optimization with Compression and Error Feedback","created":"2025-03-11","cited_by_count":4},{"id":"2505.22549","title":"DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models","created":"2025-05-28","cited_by_count":4},{"id":"2506.01352","title":"TAH-QUANT: Effective Activation Quantization in Pipeline Parallelism over Slow Network","created":"2025-06-02","cited_by_count":4},{"id":"2110.10828","title":"AdamD: Improved bias-correction in Adam","created":"2021-10-20","cited_by_count":3},{"id":"2411.11747","title":"Anisotropic Gaussian Smoothing for Gradient-based Optimization","created":"2024-11-18","cited_by_count":3},{"id":"2502.18153","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","created":"2025-02-25","cited_by_count":3},{"id":"2505.24399","title":"LightSAM: Parameter-Agnostic Sharpness-Aware Minimization","created":"2025-05-30","cited_by_count":3},{"id":"2601.22334","title":"DP-{\\lambda}CGD: Efficient Noise Correlation for Differentially Private Model Training","created":"2026-01-29","cited_by_count":3},{"id":"1805.07500","title":"GADAM: Genetic-Evolutionary ADAM for Deep Neural Network Optimization","created":"2018-05-19","cited_by_count":2},{"id":"2006.11401","title":"DEED: A General Quantization Scheme for Communication Efficiency in Bits","created":"2020-06-19","cited_by_count":2},{"id":"2203.01603","title":"AdaFamily: A family of Adam-like adaptive gradient methods","created":"2022-03-03","cited_by_count":2},{"id":"2207.02763","title":"BFE and AdaBFE: A New Approach in Learning Rate Automation for Stochastic Optimization","created":"2022-07-06","cited_by_count":2},{"id":"2403.11041","title":"FAGH: Accelerating Federated Learning with Approximated Global Hessian","created":"2024-03-16","cited_by_count":2},{"id":"2405.17470","title":"Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information","created":"2024-05-24","cited_by_count":2},{"id":"2407.01640","title":"BADM: Batch ADMM for Deep Learning","created":"2024-06-30","cited_by_count":2},{"id":"2410.24216","title":"CaAdam: Improving Adam optimizer using connection aware methods","created":"2024-10-31","cited_by_count":2},{"id":"2411.18385","title":"Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization","created":"2024-11-27","cited_by_count":2},{"id":"2411.19647","title":"CAdam: Confidence-Based Optimization for Online Learning","created":"2024-11-29","cited_by_count":2},{"id":"2412.14226","title":"FedSTaS: Client Stratification and Client Level Sampling for Efficient Federated Learning","created":"2024-12-18","cited_by_count":2},{"id":"2412.19444","title":"Towards Simple and Provable Parameter-Free Adaptive Gradient Methods","created":"2024-12-27","cited_by_count":2},{"id":"2412.20302","title":"EXAdam: The Power of Adaptive Cross-Moments","created":"2024-12-29","cited_by_count":2},{"id":"2501.07526","title":"Communication-Efficient, 2D Parallel Stochastic Gradient Descent for Distributed-Memory Optimization","created":"2025-01-13","cited_by_count":2},{"id":"2502.02727","title":"Gradient Correction in Federated Learning with Adaptive Optimization","created":"2025-02-04","cited_by_count":2},{"id":"2503.11147","title":"Asynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning","created":"2025-03-14","cited_by_count":2},{"id":"2505.21651","title":"AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent","created":"2025-05-27","cited_by_count":2},{"id":"2506.00416","title":"Blockchain-Enabled Privacy-Preserving Second-Order Federated Edge Learning in Personalized Healthcare","created":"2025-05-31","cited_by_count":2},{"id":"2506.08464","title":"MAC: An Efficient Gradient Preconditioning using Mean Activation Approximated Curvature","created":"2025-06-10","cited_by_count":2},{"id":"2506.14929","title":"FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning","created":"2025-06-17","cited_by_count":2},{"id":"2506.22479","title":"Hindsight-Guided Momentum (HGM) Optimizer: An Approach to Adaptive Learning Rate","created":"2025-06-22","cited_by_count":2},{"id":"2507.01241","title":"Beyond First-Order: Training LLMs with Stochastic Conjugate Subgradients and AdamW","created":"2025-07-01","cited_by_count":2},{"id":"2507.03545","title":"DOME: Improving Signal-to-Noise in Stochastic Gradient Descent via Sharp-Direction Subspace Filtering","created":"2025-07-04","cited_by_count":2},{"id":"2507.06125","title":"Subspace-based Approximate Hessian Method for Zeroth-Order Optimization","created":"2025-07-08","cited_by_count":2},{"id":"2507.19968","title":"Dimer-Enhanced Optimization: A First-Order Approach to Escaping Saddle Points in Neural Network Training","created":"2025-07-26","cited_by_count":2},{"id":"2508.02719","title":"ZetA: A Riemann Zeta-Scaled Extension of Adam for Deep Learning","created":"2025-08-01","cited_by_count":2},{"id":"2508.04293","title":"Comparative Analysis of Novel NIRMAL Optimizer Against Adam and SGD with Momentum","created":"2025-08-06","cited_by_count":2},{"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},{"id":"2511.20509","title":"DP-MicroAdam: Private and Frugal Algorithm for Training and Fine-tuning","created":"2025-11-25","cited_by_count":2},{"id":"1906.04819","title":"ADASS: Adaptive Sample Selection for Training Acceleration","created":"2019-06-11","cited_by_count":1},{"id":"2305.15723","title":"Learning across Data Owners with Joint Differential Privacy","created":"2023-05-25","cited_by_count":1},{"id":"2311.02818","title":"Signal Processing Meets SGD: From Momentum to Filter","created":"2023-11-06","cited_by_count":1},{"id":"2405.00252","title":"Q-Newton: Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent","created":"2024-04-30","cited_by_count":1},{"id":"2407.04235","title":"Novel Optimization Techniques for Parameter Estimation","created":"2024-07-05","cited_by_count":1},{"id":"2409.04244","title":"WarpAdam: A new Adam optimizer based on Meta-Learning approach","created":"2024-09-06","cited_by_count":1}],"next_cursor":"100"}