{"total":629,"rows":[{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2111.05849","title":"Advances in Neural Rendering","created":"2021-11-10","cited_by_count":365,"area":null},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316,"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":"2109.09831","title":"SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization","created":"2021-09-20","cited_by_count":230,"area":null},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164,"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":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151,"area":null},{"id":"2104.10201","title":"Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020","created":"2021-04-20","cited_by_count":148,"area":null},{"id":"2304.11127","title":"Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance","created":"2023-04-21","cited_by_count":147,"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":"2104.01177","title":"How Powerful are Performance Predictors in Neural Architecture Search?","created":"2021-04-02","cited_by_count":90,"area":null},{"id":"2101.01035","title":"HyperMorph: Amortized Hyperparameter Learning for Image Registration","created":"2021-01-04","cited_by_count":85,"area":null},{"id":"2206.07769","title":"HyperImpute: Generalized Iterative Imputation with Automatic Model Selection","created":"2022-06-15","cited_by_count":83,"area":null},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79,"area":null},{"id":"2106.06257","title":"HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML","created":"2021-06-11","cited_by_count":75,"area":null},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74,"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":"2109.08215","title":"Pre-trained Gaussian Processes for Bayesian Optimization","created":"2021-09-16","cited_by_count":63,"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":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2106.04502","title":"Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing","created":"2021-06-08","cited_by_count":58,"area":null},{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","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":"2309.02033","title":"Data-Juicer: A One-Stop Data Processing System for Large Language Models","created":"2023-09-05","cited_by_count":52,"area":null},{"id":"2209.14803","title":"polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics","created":"2022-09-29","cited_by_count":48,"area":null},{"id":"2106.00421","title":"OpenBox: A Generalized Black-box Optimization Service","created":"2021-06-01","cited_by_count":46,"area":null},{"id":"2204.05562","title":"FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning","created":"2022-04-12","cited_by_count":43,"area":null},{"id":"2111.02790","title":"LassoBench: A High-Dimensional Hyperparameter Optimization Benchmark Suite for Lasso","created":"2021-11-04","cited_by_count":41,"area":null},{"id":"2303.04673","title":"Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference","created":"2023-03-08","cited_by_count":40,"area":null},{"id":"2205.13881","title":"Automated Dynamic Algorithm Configuration","created":"2022-05-27","cited_by_count":39,"area":null},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2206.07438","title":"Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview","created":"2022-06-15","cited_by_count":37,"area":null},{"id":"2502.19249","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","created":"2025-02-26","cited_by_count":37,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"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":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2411.05735","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2110.05668","title":"NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks","created":"2021-10-12","cited_by_count":32,"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":"2403.07213","title":"Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits","created":"2024-03-11","cited_by_count":27,"area":null},{"id":"2210.09943","title":"Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition","created":"2022-10-18","cited_by_count":26,"area":null},{"id":"2404.16795","title":"In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization","created":"2024-04-25","cited_by_count":26,"area":null},{"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":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25,"area":null},{"id":"2210.16913","title":"Revisiting Simple Regret: Fast Rates for Returning a Good Arm","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2306.12834","title":"Natural Language Processing in Electronic Health Records in Relation to Healthcare Decision-making: A Systematic Review","created":"2023-06-22","cited_by_count":25,"area":null},{"id":"2111.13755","title":"A survey on multi-objective hyperparameter optimization algorithms for Machine Learning","created":"2021-11-23","cited_by_count":24,"area":null},{"id":"2212.03332","title":"Edge Impulse: An MLOps Platform for Tiny Machine Learning","created":"2022-11-02","cited_by_count":24,"area":null},{"id":"2101.07385","title":"Autonomous synthesis of metastable materials","created":"2021-01-19","cited_by_count":23,"area":null},{"id":"2106.04682","title":"Bayesian Optimization over Hybrid Spaces","created":"2021-06-08","cited_by_count":23,"area":null},{"id":"2106.12639","title":"Multi-objective Asynchronous Successive Halving","created":"2021-06-23","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":"2406.04824","title":"FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch","created":"2024-06-07","cited_by_count":23,"area":null},{"id":"2110.10423","title":"ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies","created":"2021-10-20","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":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2102.07108","title":"CATE: Computation-aware Neural Architecture Encoding with Transformers","created":"2021-02-14","cited_by_count":21,"area":null},{"id":"2104.08166","title":"Automatic Termination for Hyperparameter Optimization","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2107.07445","title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","created":"2021-07-15","cited_by_count":21,"area":null},{"id":"2301.01824","title":"Privacy and Efficiency of Communications in Federated Split Learning","created":"2023-01-04","cited_by_count":21,"area":null},{"id":"2111.03602","title":"NAS-Bench-x11 and the Power of Learning Curves","created":"2021-11-05","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":"2106.06079","title":"A Nonmyopic Approach to Cost-Constrained Bayesian Optimization","created":"2021-06-10","cited_by_count":19,"area":null},{"id":"2110.08616","title":"GradSign: Model Performance Inference with Theoretical Insights","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2211.01834","title":"Toward Unsupervised Outlier Model Selection","created":"2022-11-03","cited_by_count":19,"area":null},{"id":"2412.06947","title":"PyraNet: A Multi-Layered Hierarchical Dataset for Verilog","created":"2024-12-09","cited_by_count":19,"area":null},{"id":"2103.15798","title":"Rethinking Neural Operations for Diverse Tasks","created":"2021-03-29","cited_by_count":18,"area":null},{"id":"2106.16118","title":"SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo","created":"2021-06-30","cited_by_count":18,"area":null},{"id":"2102.01723","title":"Apollo: Transferable Architecture Exploration","created":"2021-02-02","cited_by_count":17,"area":null},{"id":"2103.12715","title":"Promoting Fairness through Hyperparameter Optimization","created":"2021-03-23","cited_by_count":17,"area":null},{"id":"2205.04878","title":"Hybrid quantum ResNet for car classification and its hyperparameter optimization","created":"2022-05-10","cited_by_count":17,"area":null},{"id":"2307.09943","title":"Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay","created":"2023-07-19","cited_by_count":17,"area":null},{"id":"2310.15351","title":"Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2209.08018","title":"IoT Data Analytics in Dynamic Environments: From An Automated Machine Learning Perspective","created":"2022-09-16","cited_by_count":16,"area":null},{"id":"2211.06149","title":"Combining Multi-Fidelity Modelling and Asynchronous Batch Bayesian Optimization","created":"2022-11-11","cited_by_count":16,"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":"2410.03074","title":"MetaOOD: Automatic Selection of OOD Detection Models","created":"2024-10-04","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":"2101.02696","title":"Accelerated, Optimal, and Parallel: Some Results on Model-Based Stochastic Optimization","created":"2021-01-07","cited_by_count":14,"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":"2406.03348","title":"Position: A Call to Action for a Human-Centered AutoML Paradigm","created":"2024-06-05","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":"2102.09026","title":"Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm","created":"2021-02-17","cited_by_count":13,"area":null},{"id":"2109.13800","title":"Faster Improvement Rate Population Based Training","created":"2021-09-28","cited_by_count":13,"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}],"next_cursor":"100"}