{"total":284,"rows":[{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396,"area":null},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621,"area":null},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365,"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":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145,"area":null},{"id":"2402.03921","title":"Large Language Models to Enhance Bayesian Optimization","created":"2024-02-06","cited_by_count":135,"area":null},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101,"area":null},{"id":"2202.08450","title":"Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization","created":"2022-02-17","cited_by_count":97,"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":"2107.06882","title":"Conservative Objective Models for Effective Offline Model-Based Optimization","created":"2021-07-14","cited_by_count":88,"area":null},{"id":"2206.03301","title":"Recent Advances in Bayesian Optimization","created":"2022-06-07","cited_by_count":76,"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":"2305.17535","title":"PFNs4BO: In-Context Learning for Bayesian Optimization","created":"2023-05-27","cited_by_count":73,"area":null},{"id":"2404.11599","title":"Variational Bayesian Last Layers","created":"2024-04-17","cited_by_count":69,"area":null},{"id":"2109.08215","title":"Pre-trained Gaussian Processes for Bayesian Optimization","created":"2021-09-16","cited_by_count":63,"area":null},{"id":"2211.06291","title":"Do Bayesian Neural Networks Need To Be Fully Stochastic?","created":"2022-11-11","cited_by_count":63,"area":null},{"id":"2206.04771","title":"Joint Entropy Search for Maximally-Informed Bayesian Optimization","created":"2022-06-09","cited_by_count":55,"area":null},{"id":"2210.08495","title":"Pareto Set Learning for Expensive Multi-Objective Optimization","created":"2022-10-16","cited_by_count":51,"area":null},{"id":"2305.20028","title":"A Study of Bayesian Neural Network Surrogates for Bayesian Optimization","created":"2023-05-31","cited_by_count":50,"area":null},{"id":"2203.09410","title":"A Framework and Benchmark for Deep Batch Active Learning for Regression","created":"2022-03-17","cited_by_count":49,"area":null},{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49,"area":null},{"id":"2210.02905","title":"Joint Entropy Search for Multi-objective Bayesian Optimization","created":"2022-10-06","cited_by_count":45,"area":null},{"id":"2212.04450","title":"GAUCHE: A Library for Gaussian Processes in Chemistry","created":"2022-12-06","cited_by_count":41,"area":null},{"id":"2110.14188","title":"RoMA: Robust Model Adaptation for Offline Model-based Optimization","created":"2021-10-27","cited_by_count":39,"area":null},{"id":"2203.03048","title":"Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors","created":"2022-03-06","cited_by_count":39,"area":null},{"id":"2210.01628","title":"Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimization","created":"2022-10-04","cited_by_count":37,"area":null},{"id":"2310.08252","title":"MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning","created":"2023-10-12","cited_by_count":36,"area":null},{"id":"2211.11349","title":"Data-Driven Offline Decision-Making via Invariant Representation Learning","created":"2022-11-21","cited_by_count":31,"area":null},{"id":"2110.11346","title":"Data-Driven Offline Optimization For Architecting Hardware Accelerators","created":"2021-10-20","cited_by_count":29,"area":null},{"id":"2302.05927","title":"Transfer Learning for Bayesian Optimization: A Survey","created":"2023-02-12","cited_by_count":27,"area":null},{"id":"2102.09009","title":"BORE: Bayesian Optimization by Density-Ratio Estimation","created":"2021-02-17","cited_by_count":26,"area":null},{"id":"2201.00272","title":"Thinking inside the box: A tutorial on grey-box Bayesian optimization","created":"2022-01-02","cited_by_count":26,"area":null},{"id":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26,"area":null},{"id":"2111.03577","title":"Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning","created":"2021-11-05","cited_by_count":25,"area":null},{"id":"2208.01565","title":"Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs","created":"2022-08-02","cited_by_count":25,"area":null},{"id":"2102.12466","title":"Information Directed Reward Learning for Reinforcement Learning","created":"2021-02-24","cited_by_count":24,"area":"alignment"},{"id":"2103.15254","title":"Bayesian Deep Basis Fitting for Depth Completion with Uncertainty","created":"2021-03-29","cited_by_count":23,"area":null},{"id":"2209.00517","title":"The Neural Process Family: Survey, Applications and Perspectives","created":"2022-09-01","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":"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":"2402.02355","title":"Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning","created":"2024-02-04","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":"2203.10304","title":"PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs","created":"2022-03-19","cited_by_count":20,"area":null},{"id":"2206.13035","title":"A General Recipe for Likelihood-free Bayesian Optimization","created":"2022-06-27","cited_by_count":19,"area":null},{"id":"2211.08262","title":"A mixed-categorical correlation kernel for Gaussian process","created":"2022-11-15","cited_by_count":19,"area":null},{"id":"2306.03828","title":"Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How","created":"2023-06-06","cited_by_count":18,"area":null},{"id":"2102.12810","title":"Hyperparameter Transfer Learning with Adaptive Complexity","created":"2021-02-25","cited_by_count":17,"area":null},{"id":"2105.00371","title":"Discovering Diverse Athletic Jumping Strategies","created":"2021-05-02","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":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16,"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":"2203.08734","title":"Learning Where To Look -- Generative NAS is Surprisingly Efficient","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2306.11715","title":"Multi-Fidelity Active Learning with GFlowNets","created":"2023-06-20","cited_by_count":15,"area":null},{"id":"2402.07745","title":"Predictive Churn with the Set of Good Models","created":"2024-02-12","cited_by_count":15,"area":null},{"id":"2105.14559","title":"Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle","created":"2021-05-30","cited_by_count":14,"area":null},{"id":"2206.08476","title":"Zero-Shot AutoML with Pretrained Models","created":"2022-06-16","cited_by_count":14,"area":null},{"id":"2208.13771","title":"Fast Bayesian Optimization of Needle-in-a-Haystack Problems using Zooming Memory-Based Initialization (ZoMBI)","created":"2022-08-26","cited_by_count":14,"area":null},{"id":"2403.06020","title":"Multi-conditioned Graph Diffusion for Neural Architecture Search","created":"2024-03-09","cited_by_count":14,"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":"2111.03140","title":"Multi-Objective Constrained Optimization for Energy Applications via Tree Ensembles","created":"2021-11-04","cited_by_count":12,"area":null},{"id":"2302.06495","title":"Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts","created":"2023-02-13","cited_by_count":12,"area":null},{"id":"2302.10975","title":"Improved uncertainty quantification for neural networks with Bayesian last layer","created":"2023-02-21","cited_by_count":12,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2406.05072","title":"Linearization Turns Neural Operators into Function-Valued Gaussian Processes","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2505.19350","title":"FlashMD: long-stride, universal prediction of molecular dynamics","created":"2025-05-25","cited_by_count":12,"area":null},{"id":"2104.02487","title":"Neural Process for Black-Box Model Optimization Under Bayesian Framework","created":"2021-04-03","cited_by_count":11,"area":null},{"id":"2109.00938","title":"SetMargin Loss applied to Deep Keystroke Biometrics with Circle Packing Interpretation","created":"2021-09-02","cited_by_count":11,"area":null},{"id":"2207.10415","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2210.01383","title":"Generalizing Bayesian Optimization with Decision-theoretic Entropies","created":"2022-10-04","cited_by_count":11,"area":null},{"id":"2402.04005","title":"Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2404.16551","title":"Surprisingly Strong Performance Prediction with Neural Graph Features","created":"2024-04-25","cited_by_count":11,"area":null},{"id":"2112.04620","title":"Online Calibrated and Conformal Prediction Improves Bayesian Optimization","created":"2021-12-08","cited_by_count":10,"area":null},{"id":"2206.08366","title":"Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation","created":"2022-06-16","cited_by_count":10,"area":null},{"id":"2207.01566","title":"General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2304.08309","title":"Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization","created":"2023-04-17","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":"2404.17249","title":"Making Better Use of Unlabelled Data in Bayesian Active Learning","created":"2024-04-26","cited_by_count":10,"area":null},{"id":"2107.12910","title":"Sparse Bayesian Deep Learning for Dynamic System Identification","created":"2021-07-27","cited_by_count":9,"area":null},{"id":"2110.00944","title":"Kalman Bayesian Neural Networks for Closed-form Online Learning","created":"2021-10-03","cited_by_count":9,"area":null},{"id":"2203.00089","title":"Amortized Proximal Optimization","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2209.10715","title":"Batch Bayesian optimisation via density-ratio estimation with guarantees","created":"2022-09-22","cited_by_count":9,"area":null},{"id":"2210.01071","title":"New Paradigms for Exploiting Parallel Experiments in Bayesian Optimization","created":"2022-10-03","cited_by_count":9,"area":null},{"id":"2306.14348","title":"Collaborative and Distributed Bayesian Optimization via Consensus: Showcasing the Power of Collaboration for Optimal Design","created":"2023-06-25","cited_by_count":9,"area":null},{"id":"2106.00942","title":"JUMBO: Scalable Multi-task Bayesian Optimization using Offline Data","created":"2021-06-02","cited_by_count":8,"area":null},{"id":"2311.06130","title":"High-dimensional mixed-categorical Gaussian processes with application to multidisciplinary design optimization for a green aircraft","created":"2023-11-10","cited_by_count":8,"area":null},{"id":"2405.16730","title":"\"Noisier\" Noise Contrastive Eestimation is (Almost) Maximum Likelihood","created":"2024-05-27","cited_by_count":8,"area":null},{"id":"2406.04308","title":"Approximation-Aware Bayesian Optimization","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2412.20375","title":"Scalable Bayesian Optimization via Focalized Sparse Gaussian Processes","created":"2024-12-29","cited_by_count":8,"area":null},{"id":"2101.09300","title":"A Novel Genetic Algorithm with Hierarchical Evaluation Strategy for Hyperparameter Optimisation of Graph Neural Networks","created":"2021-01-22","cited_by_count":7,"area":null},{"id":"2103.08026","title":"A Scalable Gradient-Free Method for Bayesian Experimental Design with Implicit Models","created":"2021-03-14","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":"2111.07952","title":"Stochastic Gradient Line Bayesian Optimization for Efficient Noise-Robust Optimization of Parameterized Quantum Circuits","created":"2021-11-15","cited_by_count":7,"area":null},{"id":"2201.08539","title":"AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models","created":"2022-01-21","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":"2208.12754","title":"Task Selection for AutoML System Evaluation","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2209.09655","title":"Lower Bounds on the Worst-Case Complexity of Efficient Global Optimization","created":"2022-09-20","cited_by_count":7,"area":null},{"id":"2211.09100","title":"Global Optimization with Parametric Function Approximation","created":"2022-11-16","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":"2504.04204","title":"Adaptive Elicitation of Latent Information Using Natural Language","created":"2025-04-05","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}],"next_cursor":"100"}