{"total":283,"rows":[{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265,"area":null},{"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":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172,"area":null},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111,"area":null},{"id":"2205.10287","title":"On the SDEs and Scaling Rules for Adaptive Gradient Algorithms","created":"2022-05-20","cited_by_count":104,"area":null},{"id":"2112.02761","title":"BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery","created":"2021-12-06","cited_by_count":68,"area":null},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64,"area":null},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53,"area":null},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47,"area":null},{"id":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46,"area":null},{"id":"2501.16371","title":"Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks","created":"2025-01-22","cited_by_count":42,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2310.20496","title":"BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis","created":"2023-10-31","cited_by_count":41,"area":null},{"id":"2106.08208","title":"SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients","created":"2021-06-15","cited_by_count":40,"area":null},{"id":"2111.15121","title":"Pyramid Adversarial Training Improves ViT Performance","created":"2021-11-30","cited_by_count":39,"area":null},{"id":"2303.00800","title":"Continuous-Time Functional Diffusion Processes","created":"2023-03-01","cited_by_count":39,"area":"diffusion"},{"id":"2307.02047","title":"CAME: Confidence-guided Adaptive Memory Efficient Optimization","created":"2023-07-05","cited_by_count":36,"area":null},{"id":"2106.11396","title":"BiAdam: Fast Adaptive Bilevel Optimization Methods","created":"2021-06-21","cited_by_count":33,"area":null},{"id":"2503.10537","title":"Structured Preconditioners in Adaptive Optimization: A Unified Analysis","created":"2025-03-13","cited_by_count":33,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2106.02305","title":"Local Adaptivity in Federated Learning: Convergence and Consistency","created":"2021-06-04","cited_by_count":31,"area":null},{"id":"2211.15055","title":"AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning","created":"2022-11-28","cited_by_count":31,"area":null},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31,"area":null},{"id":"2106.07162","title":"Goal-Aware Neural SAT Solver","created":"2021-06-14","cited_by_count":28,"area":null},{"id":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27,"area":null},{"id":"2105.03918","title":"Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics","created":"2021-05-09","cited_by_count":26,"area":null},{"id":"2107.10879","title":"Discovering Sparse Interpretable Dynamics from Partial Observations","created":"2021-07-22","cited_by_count":25,"area":null},{"id":"2110.09714","title":"Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information","created":"2021-10-19","cited_by_count":25,"area":null},{"id":"2312.15184","title":"ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization","created":"2023-12-23","cited_by_count":25,"area":null},{"id":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2303.05916","title":"GECCO: Geometrically-Conditioned Point Diffusion Models","created":"2023-03-10","cited_by_count":24,"area":"diffusion"},{"id":"2305.07583","title":"MoMo: Momentum Models for Adaptive Learning Rates","created":"2023-05-12","cited_by_count":24,"area":null},{"id":"2409.16223","title":"Fine-Tuning is Fine, if Calibrated","created":"2024-09-24","cited_by_count":24,"area":null},{"id":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23,"area":"deeprl"},{"id":"2111.13844","title":"Adaptive Image Transformations for Transfer-based Adversarial Attack","created":"2021-11-27","cited_by_count":22,"area":null},{"id":"2305.03938","title":"Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees","created":"2023-05-06","cited_by_count":22,"area":null},{"id":"2210.13834","title":"Stable Deep MRI Reconstruction using Generative Priors","created":"2022-10-25","cited_by_count":21,"area":null},{"id":"2306.13421","title":"Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval","created":"2023-06-23","cited_by_count":20,"area":"rag"},{"id":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20,"area":null},{"id":"2108.08688","title":"Contrastive Language-Image Pre-training for the Italian Language","created":"2021-08-19","cited_by_count":19,"area":null},{"id":"2211.05910","title":"Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report","created":"2022-11-07","cited_by_count":16,"area":null},{"id":"2402.04553","title":"Curvature-Informed SGD via General Purpose Lie-Group Preconditioners","created":"2024-02-07","cited_by_count":16,"area":null},{"id":"2202.06009","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","created":"2022-02-12","cited_by_count":15,"area":null},{"id":"2510.01755","title":"Learning Regularization Functionals for Inverse Problems: A Comparative Study","created":"2025-10-02","cited_by_count":15,"area":null},{"id":"2404.09466","title":"Scoring Time Intervals using Non-Hierarchical Transformer For Automatic Piano Transcription","created":"2024-04-15","cited_by_count":14,"area":null},{"id":"2405.16397","title":"AdaFisher: Adaptive Second Order Optimization via Fisher Information","created":"2024-05-26","cited_by_count":14,"area":null},{"id":"2405.20763","title":"Improving Generalization and Convergence by Enhancing Implicit Regularization","created":"2024-05-31","cited_by_count":14,"area":null},{"id":"2106.16101","title":"AdaGDA: Faster Adaptive Gradient Descent Ascent Methods for Minimax Optimization","created":"2021-06-30","cited_by_count":13,"area":null},{"id":"2506.14562","title":"AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs","created":"2025-06-17","cited_by_count":13,"area":null},{"id":"2102.03726","title":"Adversarial example generation with AdaBelief Optimizer and Crop Invariance","created":"2021-02-07","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":"2201.06714","title":"AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization","created":"2022-01-18","cited_by_count":11,"area":null},{"id":"2209.06302","title":"Optimization without Backpropagation","created":"2022-09-13","cited_by_count":11,"area":null},{"id":"2210.05956","title":"Towards Theoretically Inspired Neural Initialization Optimization","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2110.07305","title":"DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networks","created":"2021-10-14","cited_by_count":10,"area":null},{"id":"2205.08383","title":"Bias and Fairness on Multimodal Emotion Detection Algorithms","created":"2022-05-11","cited_by_count":10,"area":null},{"id":"2310.19463","title":"Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal","created":"2023-10-30","cited_by_count":10,"area":"offlinerl"},{"id":"2105.10190","title":"AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks","created":"2021-05-21","cited_by_count":9,"area":null},{"id":"2111.07671","title":"NeuralPDE: Modelling Dynamical Systems from Data","created":"2021-11-15","cited_by_count":9,"area":null},{"id":"2211.04422","title":"Black Box Lie Group Preconditioners for SGD","created":"2022-11-08","cited_by_count":9,"area":null},{"id":"2402.09240","title":"Switch EMA: A Free Lunch for Better Flatness and Sharpness","created":"2024-02-14","cited_by_count":9,"area":null},{"id":"2405.02154","title":"Neural Context Flows for Meta-Learning of Dynamical Systems","created":"2024-05-03","cited_by_count":9,"area":null},{"id":"2411.01713","title":"Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models","created":"2024-11-03","cited_by_count":9,"area":null},{"id":"2602.17162","title":"JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures","created":"2026-02-19","cited_by_count":9,"area":null},{"id":"2106.15550","title":"Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2201.11989","title":"Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule","created":"2022-01-28","cited_by_count":8,"area":null},{"id":"2206.07394","title":"Efficient Adaptive Ensembling for Image Classification","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2208.08672","title":"RRWaveNet: A Compact End-to-End Multi-Scale Residual CNN for Robust PPG Respiratory Rate Estimation","created":"2022-08-18","cited_by_count":8,"area":null},{"id":"2302.00195","title":"Weight Prediction Boosts the Convergence of AdamW","created":"2023-02-01","cited_by_count":8,"area":null},{"id":"2305.08396","title":"MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation","created":"2023-05-15","cited_by_count":8,"area":null},{"id":"2410.22101","title":"Hyperspectral Imaging-Based Perception in Autonomous Driving Scenarios: Benchmarking Baseline Semantic Segmentation Models","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2505.11840","title":"On the $O(\\frac{\\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\\ell_1$ Norm","created":"2025-05-17","cited_by_count":8,"area":null},{"id":"2509.26337","title":"FedMuon: Federated Learning with Bias-corrected LMO-based Optimization","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2105.06421","title":"Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation","created":"2021-05-13","cited_by_count":7,"area":null},{"id":"2110.01543","title":"Stochastic Anderson Mixing for Nonconvex Stochastic Optimization","created":"2021-10-04","cited_by_count":7,"area":null},{"id":"2206.01009","title":"Unified Recurrence Modeling for Video Action Anticipation","created":"2022-06-02","cited_by_count":7,"area":null},{"id":"2211.01122","title":"Fast Adaptive Federated Bilevel Optimization","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2306.14522","title":"Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2310.04701","title":"Twin Graph-based Anomaly Detection via Attentive Multi-Modal Learning for Microservice System","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2104.08665","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","created":"2021-04-17","cited_by_count":6,"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":"2107.03331","title":"KOALA: A Kalman Optimization Algorithm with Loss Adaptivity","created":"2021-07-07","cited_by_count":6,"area":null},{"id":"2303.03984","title":"Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization","created":"2023-03-07","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":"2310.12653","title":"Product of Gaussian Mixture Diffusion Models","created":"2023-10-19","cited_by_count":6,"area":"diffusion"},{"id":"2401.08893","title":"MADA: Meta-Adaptive Optimizers through hyper-gradient Descent","created":"2024-01-17","cited_by_count":6,"area":null},{"id":"2406.01959","title":"Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2506.11982","title":"Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders","created":"2025-06-13","cited_by_count":6,"area":null},{"id":"2509.10384","title":"Flow Straight and Fast in Hilbert Space: Functional Rectified Flow","created":"2025-09-12","cited_by_count":6,"area":"diffusion"},{"id":"2606.04662","title":"Why Muon Outperforms Adam: A Curvature Perspective","created":"2026-06-03","cited_by_count":6,"area":null},{"id":"2102.11013","title":"Multiple-shooting adjoint method for whole-brain dynamic causal modeling","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2111.08462","title":"Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations","created":"2021-11-14","cited_by_count":5,"area":null},{"id":"2202.08708","title":"Learning stochastic dynamics and predicting emergent behavior using transformers","created":"2022-02-17","cited_by_count":5,"area":null},{"id":"2210.06364","title":"AdaNorm: Adaptive Gradient Norm Correction based Optimizer for CNNs","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2210.13583","title":"Learning Latent Structural Causal Models","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2211.07303","title":"Adaptive Federated Minimax Optimization with Lower Complexities","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2305.18240","title":"XGrad: Boosting Gradient-Based Optimizers With Weight Prediction","created":"2023-05-26","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}],"next_cursor":"100"}