{"total":90,"rows":[{"id":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145,"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":"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":"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":"2310.20447","title":"Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks","created":"2023-10-31","cited_by_count":37,"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":"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":"2404.16795","title":"In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization","created":"2024-04-25","cited_by_count":26,"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":"2203.08212","title":"AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2104.08166","title":"Automatic Termination for Hyperparameter Optimization","created":"2021-04-16","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":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19,"area":null},{"id":"2104.11667","title":"Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structure","created":"2021-04-23","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":"2409.15844","title":"Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection","created":"2024-09-24","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":"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},{"id":"2604.20938","title":"HARBOR: Automated Harness Optimization","created":"2026-04-22","cited_by_count":11,"area":"agents"},{"id":"2108.04541","title":"Accelerating Evolutionary Neural Architecture Search via Multi-Fidelity Evaluation","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2305.03623","title":"Optimizing Hyperparameters with Conformal Quantile Regression","created":"2023-05-05","cited_by_count":10,"area":null},{"id":"2410.09239","title":"Scaling Gaussian Processes for Learning Curve Prediction via Latent Kronecker Structure","created":"2024-10-11","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":"2203.00089","title":"Amortized Proximal Optimization","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2503.21023","title":"Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework","created":"2025-03-26","cited_by_count":9,"area":null},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2109.07563","title":"Non-smooth Bayesian Optimization in Tuning Problems","created":"2021-09-15","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":"2505.14903","title":"When to retrain a machine learning model","created":"2025-05-20","cited_by_count":8,"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":"2206.02663","title":"TransBO: Hyperparameter Optimization via Two-Phase Transfer Learning","created":"2022-06-06","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":"2405.15393","title":"Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2106.09884","title":"Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks","created":"2021-06-18","cited_by_count":6,"area":null},{"id":"2206.03966","title":"FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization","created":"2022-06-08","cited_by_count":6,"area":null},{"id":"2104.12365","title":"Efficient Hyperparameter Optimization for Physics-based Character Animation","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2202.05397","title":"Neural Architecture Search for Energy Efficient Always-on Audio Models","created":"2022-02-09","cited_by_count":5,"area":null},{"id":"2412.15554","title":"Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation","created":"2024-12-20","cited_by_count":5,"area":null},{"id":"2106.09179","title":"Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation","created":"2021-06-17","cited_by_count":4,"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":"2101.06590","title":"Cost-Efficient Online Hyperparameter Optimization","created":"2021-01-17","cited_by_count":2,"area":null},{"id":"2403.19459","title":"NeuroLGP-SM: A Surrogate-assisted Neuroevolution Approach using Linear Genetic Programming","created":"2024-03-28","cited_by_count":2,"area":null},{"id":"2405.17918","title":"Cost-Sensitive Multi-Fidelity Bayesian Optimization with Transfer of Learning Curve Extrapolation","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2502.06789","title":"Information-theoretic Bayesian Optimization: Survey and Tutorial","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2508.19733","title":"Tune My Adam, Please!","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2510.16743","title":"Zero-Shot Performance Prediction for Probabilistic Scaling Laws","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2510.21379","title":"Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2601.19831","title":"Neural Neural Scaling Laws","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2601.21624","title":"Training Memory in Deep Neural Networks: Mechanisms, Evidence, and Measurement Gaps","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2603.11149","title":"Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models","created":"2026-03-11","cited_by_count":2,"area":"safety"},{"id":"2605.07572","title":"Open-Ended Task Discovery via Bayesian Optimization","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.26248","title":"Unified Neural Scaling Laws","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2101.04185","title":"PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search","created":"2021-01-11","cited_by_count":1,"area":null},{"id":"2104.10746","title":"Automatic model training under restrictive time constraints","created":"2021-04-21","cited_by_count":1,"area":null},{"id":"2203.01717","title":"Practitioner Motives to Use Different Hyperparameter Optimization Methods","created":"2022-03-03","cited_by_count":1,"area":null},{"id":"2207.14174","title":"Bayesian Optimization-Based Beam Alignment for MmWave MIMO Communication Systems","created":"2022-07-28","cited_by_count":1,"area":null},{"id":"2208.02821","title":"Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round","created":"2022-08-04","cited_by_count":1,"area":null},{"id":"2301.10443","title":"Learning to Rank Normalized Entropy Curves with Differentiable Window Transformation","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2304.02497","title":"Hyper-parameter Tuning for Adversarially Robust Models","created":"2023-04-05","cited_by_count":1,"area":null},{"id":"2306.00357","title":"Efficient and Robust Bayesian Selection of Hyperparameters in Dimension Reduction for Visualization","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2404.08786","title":"NeuroLGP-SM: Scalable Surrogate-Assisted Neuroevolution for Deep Neural Networks","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2405.15303","title":"A Trajectory-Based Bayesian Approach to Multi-Objective Hyperparameter Optimization with Epoch-Aware Trade-Offs","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2409.00584","title":"FastBO: Fast HPO and NAS with Adaptive Fidelity Identification","created":"2024-09-01","cited_by_count":1,"area":null},{"id":"2505.15657","title":"LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.23032","title":"Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2604.08891","title":"Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2608.23860","title":"Revelation Control","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2109.14925","title":"Genealogical Population-Based Training for Hyperparameter Optimization","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2204.04831","title":"Cello: Efficient Computer Systems Optimization with Predictive Early Termination and Censored Regression","created":"2022-04-11","cited_by_count":0,"area":null},{"id":"2311.11717","title":"Can we infer the presence of Differential Privacy in Deep Learning models' weights? Towards more secure Deep Learning","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2402.05025","title":"Strong convexity-guided hyper-parameter optimization for flatter losses","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2407.13685","title":"Beyond Trend Following: Deep Learning for Market Trend Prediction","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2410.07696","title":"Meta-Learning from Learning Curves for Budget-Limited Algorithm Selection","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2506.04349","title":"You Only Train Once","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2601.01383","title":"Data Complexity-aware Deep Model Performance Forecasting","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2601.03166","title":"Dynamic Hyperparameter Importance for Efficient Multi-Objective Optimization","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2602.12082","title":"Empirical Gaussian Processes","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2605.17234","title":"Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.20442","title":"Evolutionary Two-Stage Hyperparameter Optimization Strategies for Physics-Informed Neural Networks","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.16409","title":"SoftModel: A Neural Model That Grows Its Own Topology -- Governed Structural Growth for Continual In-Service Learning","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.13533","title":"Early-Stopping Thresholds for ES-HyperNEAT: A Data-Driven Approach from Fitness Dynamics","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.18996","title":"Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2609.19437","title":"Bayesian Optimization with Rich Auxiliary Information via LLMs","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.23549","title":"Physics-residual machine learning predicts oxygen-evolution catalyst activity beyond the training range from sparse polarization measurements","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.35827","title":"Meta-learning accelerates detector design optimization","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.09621","title":"When does a network's training history predict its future learning better than its current state? Evidence from a response probe and a forecasting screen","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.14625","title":"From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}