{"total":221,"rows":[{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149,"area":null},{"id":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2109.06716","title":"HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO","created":"2021-09-14","cited_by_count":112,"area":null},{"id":"2101.01035","title":"HyperMorph: Amortized Hyperparameter Learning for Image Registration","created":"2021-01-04","cited_by_count":85,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2109.03670","title":"YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimization","created":"2021-09-08","cited_by_count":62,"area":null},{"id":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59,"area":null},{"id":"2207.12560","title":"AMLB: an AutoML Benchmark","created":"2022-07-25","cited_by_count":55,"area":null},{"id":"2112.13835","title":"Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2203.16680","title":"Learning the Effect of Registration Hyperparameters with HyperMorph","created":"2022-03-30","cited_by_count":35,"area":null},{"id":"2306.12370","title":"PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning","created":"2023-06-21","cited_by_count":31,"area":null},{"id":"2201.12150","title":"Learning Curves for Decision Making in Supervised Machine Learning: A Survey","created":"2022-01-28","cited_by_count":27,"area":null},{"id":"2504.04365","title":"AutoPDL: Automatic Prompt Optimization for LLM Agents","created":"2025-04-06","cited_by_count":27,"area":"agents"},{"id":"2107.08861","title":"VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2111.05850","title":"Towards Green Automated Machine Learning: Status Quo and Future Directions","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2203.15207","title":"Generalizing Few-Shot NAS with Gradient Matching","created":"2022-03-29","cited_by_count":25,"area":null},{"id":"2106.12639","title":"Multi-objective Asynchronous Successive Halving","created":"2021-06-23","cited_by_count":23,"area":null},{"id":"2310.05055","title":"FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis","created":"2023-10-08","cited_by_count":23,"area":null},{"id":"2402.17457","title":"Super Consistency of Neural Network Landscapes and Learning Rate Transfer","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2102.11860","title":"Automated Discovery of Adaptive Attacks on Adversarial Defenses","created":"2021-02-23","cited_by_count":22,"area":null},{"id":"2203.08212","title":"AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2207.09405","title":"Bayesian Generational Population-Based Training","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2105.01015","title":"Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization","created":"2021-05-03","cited_by_count":19,"area":null},{"id":"2103.12715","title":"Promoting Fairness through Hyperparameter Optimization","created":"2021-03-23","cited_by_count":17,"area":null},{"id":"2302.00441","title":"Scaling Laws for Hyperparameter Optimization","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2303.08485","title":"Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML","created":"2023-03-15","cited_by_count":16,"area":null},{"id":"2111.13914","title":"Fast and Informative Model Selection using Learning Curve Cross-Validation","created":"2021-11-27","cited_by_count":15,"area":null},{"id":"2202.09774","title":"Supervising the Multi-Fidelity Race of Hyperparameter Configurations","created":"2022-02-20","cited_by_count":15,"area":null},{"id":"2105.10762","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","created":"2021-05-22","cited_by_count":14,"area":null},{"id":"2112.08524","title":"FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning","created":"2021-12-15","cited_by_count":14,"area":null},{"id":"2205.05511","title":"Efficient Automated Deep Learning for Time Series Forecasting","created":"2022-05-11","cited_by_count":14,"area":null},{"id":"2205.08835","title":"Fair and Green Hyperparameter Optimization via Multi-objective and Multiple Information Source Bayesian Optimization","created":"2022-05-18","cited_by_count":14,"area":null},{"id":"2206.03493","title":"DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning","created":"2022-06-07","cited_by_count":14,"area":null},{"id":"2412.17622","title":"Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms","created":"2024-12-23","cited_by_count":14,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2201.06834","title":"Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale","created":"2022-01-18","cited_by_count":13,"area":null},{"id":"2206.02511","title":"Transfer Learning based Search Space Design for Hyperparameter Tuning","created":"2022-06-06","cited_by_count":13,"area":null},{"id":"2207.06940","title":"PASHA: Efficient HPO and NAS with Progressive Resource Allocation","created":"2022-07-14","cited_by_count":13,"area":null},{"id":"2608.07545","title":"DarwinX: Evolving Agent Harnesses Through Natural Selection","created":"2026-07-31","cited_by_count":13,"area":"agents"},{"id":"2105.13059","title":"Efficient and Generalizable Tuning Strategies for Stochastic Gradient MCMC","created":"2021-05-27","cited_by_count":11,"area":null},{"id":"2305.03623","title":"Optimizing Hyperparameters with Conformal Quantile Regression","created":"2023-05-05","cited_by_count":10,"area":null},{"id":"2412.07820","title":"Hyperband-based Bayesian Optimization for Black-box Prompt Selection","created":"2024-12-10","cited_by_count":10,"area":null},{"id":"2108.08019","title":"RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving","created":"2021-08-18","cited_by_count":9,"area":null},{"id":"2201.05000","title":"Automated Reinforcement Learning: An Overview","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2302.01539","title":"A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization","created":"2023-02-03","cited_by_count":9,"area":null},{"id":"2406.03033","title":"Optimal Multi-Fidelity Best-Arm Identification","created":"2024-06-05","cited_by_count":9,"area":null},{"id":"2111.14514","title":"Naive Automated Machine Learning","created":"2021-11-29","cited_by_count":8,"area":null},{"id":"2202.09036","title":"Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation","created":"2022-02-18","cited_by_count":8,"area":null},{"id":"2203.01400","title":"Adaptive Gradient Methods with Local Guarantees","created":"2022-03-02","cited_by_count":8,"area":null},{"id":"2206.12708","title":"Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach","created":"2022-06-25","cited_by_count":8,"area":null},{"id":"2307.02295","title":"Meta-Learning Adversarial Bandit Algorithms","created":"2023-07-05","cited_by_count":8,"area":null},{"id":"2510.15262","title":"Robust Layerwise Scaling Rules by Proper Weight Decay Tuning","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2102.02344","title":"Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models","created":"2021-02-03","cited_by_count":7,"area":null},{"id":"2110.10461","title":"Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation","created":"2021-10-20","cited_by_count":7,"area":null},{"id":"2304.11153","title":"Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2306.11363","title":"Masked Diffusion Models Are Fast Distribution Learners","created":"2023-06-20","cited_by_count":7,"area":"diffusion"},{"id":"2405.15393","title":"Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2504.16005","title":"CAPO: Cost-Aware Prompt Optimization","created":"2025-04-22","cited_by_count":7,"area":null},{"id":"2108.12738","title":"SummerTime: Text Summarization Toolkit for Non-experts","created":"2021-08-29","cited_by_count":6,"area":null},{"id":"2212.00333","title":"AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration","created":"2022-12-01","cited_by_count":6,"area":null},{"id":"2306.07761","title":"Multi-Fidelity Multi-Armed Bandits Revisited","created":"2023-06-13","cited_by_count":6,"area":null},{"id":"2307.15422","title":"Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?","created":"2023-07-28","cited_by_count":6,"area":null},{"id":"2309.02202","title":"On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence","created":"2023-09-05","cited_by_count":6,"area":null},{"id":"2402.09638","title":"Multi-Fidelity Methods for Optimization: A Survey","created":"2024-02-15","cited_by_count":6,"area":null},{"id":"2405.03389","title":"Don't Waste Your Time: Early Stopping Cross-Validation","created":"2024-05-06","cited_by_count":6,"area":null},{"id":"2601.21795","title":"Effective LoRA Adapter Routing using Task Representations","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2607.18235","title":"Automated Discovery Has No Universally Superior Harness","created":"2026-07-20","cited_by_count":6,"area":null},{"id":"2103.16111","title":"A resource-efficient method for repeated HPO and NAS problems","created":"2021-03-30","cited_by_count":5,"area":null},{"id":"2202.04487","title":"Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget","created":"2022-02-09","cited_by_count":5,"area":null},{"id":"2208.09884","title":"DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination","created":"2022-08-21","cited_by_count":5,"area":null},{"id":"2310.02540","title":"Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data","created":"2023-10-04","cited_by_count":5,"area":null},{"id":"2404.04111","title":"The Unreasonable Effectiveness Of Early Discarding After One Epoch In Neural Network Hyperparameter Optimization","created":"2024-04-05","cited_by_count":5,"area":null},{"id":"2405.00319","title":"Data Augmentation Policy Search for Long-Term Forecasting","created":"2024-05-01","cited_by_count":5,"area":null},{"id":"2405.02267","title":"Structural Pruning of Pre-trained Language Models via Neural Architecture Search","created":"2024-05-03","cited_by_count":5,"area":null},{"id":"2406.18630","title":"Improving Hyperparameter Optimization with Checkpointed Model Weights","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2108.02479","title":"HyperJump: Accelerating HyperBand via Risk Modelling","created":"2021-08-05","cited_by_count":4,"area":null},{"id":"2111.14756","title":"Automated Benchmark-Driven Design and Explanation of Hyperparameter Optimizers","created":"2021-11-29","cited_by_count":4,"area":null},{"id":"2205.06807","title":"Transformation-Interaction-Rational Representation for Symbolic Regression","created":"2022-04-25","cited_by_count":4,"area":null},{"id":"2207.06216","title":"Goal-Oriented Sensitivity Analysis of Hyperparameters in Deep Learning","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2306.01436","title":"Multi-Objective Population Based Training","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2306.17630","title":"Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2402.17440","title":"Principled Architecture-aware Scaling of Hyperparameters","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2502.04030","title":"Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging","created":"2025-02-06","cited_by_count":4,"area":"lr"},{"id":"2201.09798","title":"IMO$^3$: Interactive Multi-Objective Off-Policy Optimization","created":"2022-01-24","cited_by_count":3,"area":null},{"id":"2204.01457","title":"SHiFT: An Efficient, Flexible Search Engine for Transfer Learning","created":"2022-04-04","cited_by_count":3,"area":null},{"id":"2208.00204","title":"Tackling Neural Architecture Search With Quality Diversity Optimization","created":"2022-07-30","cited_by_count":3,"area":null},{"id":"2210.10659","title":"Review of the state of the art in autonomous artificial intelligence","created":"2022-10-17","cited_by_count":3,"area":null},{"id":"2212.07551","title":"Faster Maximum Inner Product Search in High Dimensions","created":"2022-12-14","cited_by_count":3,"area":null},{"id":"2310.11478","title":"ASP: Automatic Selection of Proxy dataset for efficient AutoML","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2311.08430","title":"Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2402.19090","title":"Best Arm Identification with Resource Constraints","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2404.01965","title":"Towards Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural Networks","created":"2024-04-02","cited_by_count":3,"area":null},{"id":"2505.16561","title":"Auto-nnU-Net: Towards Automated Medical Image Segmentation","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2505.19205","title":"OptiMindTune: A Multi-Agent Framework for Intelligent Hyperparameter Optimization","created":"2025-05-25","cited_by_count":3,"area":"agents"}],"next_cursor":"100"}