{"total":427,"rows":[{"id":"2402.03921","title":"Large Language Models to Enhance Bayesian Optimization","created":"2024-02-06","cited_by_count":135,"area":null},{"id":"2103.12959","title":"Solving and Learning Nonlinear PDEs with Gaussian Processes","created":"2021-03-24","cited_by_count":129,"area":null},{"id":"2106.02584","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","created":"2021-06-04","cited_by_count":113,"area":null},{"id":"2102.08501","title":"DEUP: Direct Epistemic Uncertainty Prediction","created":"2021-02-16","cited_by_count":104,"area":null},{"id":"2305.19590","title":"Neural Kernel Surface Reconstruction","created":"2023-05-31","cited_by_count":104,"area":null},{"id":"2203.12742","title":"Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders","created":"2022-03-23","cited_by_count":102,"area":null},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101,"area":null},{"id":"2102.11409","title":"On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty","created":"2021-02-22","cited_by_count":87,"area":null},{"id":"2102.12108","title":"The Promises and Pitfalls of Deep Kernel Learning","created":"2021-02-24","cited_by_count":81,"area":null},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81,"area":null},{"id":"2201.11872","title":"Local Latent Space Bayesian Optimization over Structured Inputs","created":"2022-01-28","cited_by_count":79,"area":null},{"id":"2106.15482","title":"Personalized Federated Learning with Gaussian Processes","created":"2021-06-29","cited_by_count":76,"area":null},{"id":"2307.14338","title":"TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023","created":"2023-07-26","cited_by_count":74,"area":null},{"id":"2101.07667","title":"Few-Shot Bayesian Optimization with Deep Kernel Surrogates","created":"2021-01-19","cited_by_count":71,"area":null},{"id":"2404.11599","title":"Variational Bayesian Last Layers","created":"2024-04-17","cited_by_count":69,"area":null},{"id":"2402.00809","title":"Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI","created":"2024-02-01","cited_by_count":62,"area":null},{"id":"2111.13674","title":"Neural Fields as Learnable Kernels for 3D Reconstruction","created":"2021-11-26","cited_by_count":58,"area":null},{"id":"2202.11678","title":"Bayesian Model Selection, the Marginal Likelihood, and Generalization","created":"2022-02-23","cited_by_count":57,"area":null},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2106.03609","title":"High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning","created":"2021-06-07","cited_by_count":54,"area":null},{"id":"2206.03992","title":"Neural Diffusion Processes","created":"2022-06-08","cited_by_count":50,"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":"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":"2402.05015","title":"A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?","created":"2024-02-07","cited_by_count":48,"area":null},{"id":"2203.16481","title":"On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification","created":"2022-03-30","cited_by_count":46,"area":null},{"id":"2102.05829","title":"Causal Inference for Time series Analysis: Problems, Methods and Evaluation","created":"2021-02-11","cited_by_count":42,"area":null},{"id":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42,"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":"2205.10060","title":"The Unreasonable Effectiveness of Deep Evidential Regression","created":"2022-05-20","cited_by_count":40,"area":null},{"id":"2212.09184","title":"Faithful Heteroscedastic Regression with Neural Networks","created":"2022-12-18","cited_by_count":37,"area":null},{"id":"2301.12844","title":"Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?","created":"2023-01-30","cited_by_count":36,"area":null},{"id":"2103.01439","title":"Fast Adaptation with Linearized Neural Networks","created":"2021-03-02","cited_by_count":32,"area":null},{"id":"2210.01883","title":"Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions","created":"2022-10-04","cited_by_count":32,"area":null},{"id":"2304.01294","title":"Sparse Cholesky Factorization for Solving Nonlinear PDEs via Gaussian Processes","created":"2023-04-03","cited_by_count":31,"area":null},{"id":"2111.02275","title":"Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data","created":"2021-11-03","cited_by_count":28,"area":null},{"id":"2107.05757","title":"Kernel Continual Learning","created":"2021-07-12","cited_by_count":27,"area":null},{"id":"2205.00165","title":"NeuralEF: Deconstructing Kernels by Deep Neural Networks","created":"2022-04-30","cited_by_count":27,"area":null},{"id":"2302.05927","title":"Transfer Learning for Bayesian Optimization: A Survey","created":"2023-02-12","cited_by_count":27,"area":null},{"id":"2305.04933","title":"Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial","created":"2023-05-07","cited_by_count":27,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2102.07868","title":"GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning","created":"2021-02-15","cited_by_count":26,"area":null},{"id":"2207.01066","title":"NP-Match: When Neural Processes meet Semi-Supervised Learning","created":"2022-07-03","cited_by_count":25,"area":null},{"id":"2402.02949","title":"Kernel PCA for Out-of-Distribution Detection","created":"2024-02-05","cited_by_count":24,"area":null},{"id":"2104.06135","title":"Multivariate Deep Evidential Regression","created":"2021-04-13","cited_by_count":23,"area":null},{"id":"2106.03195","title":"Meta-Learning Reliable Priors in the Function Space","created":"2021-06-06","cited_by_count":23,"area":null},{"id":"2208.00306","title":"Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation","created":"2022-07-30","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":"2206.03314","title":"Integrating Random Effects in Deep Neural Networks","created":"2022-06-07","cited_by_count":22,"area":null},{"id":"2106.07512","title":"Last Layer Marginal Likelihood for Invariance Learning","created":"2021-06-14","cited_by_count":21,"area":null},{"id":"2205.02708","title":"Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction","created":"2022-05-05","cited_by_count":21,"area":null},{"id":"2205.06342","title":"Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning","created":"2022-05-12","cited_by_count":21,"area":null},{"id":"2303.02444","title":"Calibrating Transformers via Sparse Gaussian Processes","created":"2023-03-04","cited_by_count":21,"area":null},{"id":"2305.04962","title":"Error Analysis of Kernel/GP Methods for Nonlinear and Parametric PDEs","created":"2023-05-08","cited_by_count":21,"area":null},{"id":"2205.06130","title":"Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models","created":"2022-05-12","cited_by_count":20,"area":null},{"id":"2504.14889","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","created":"2025-04-21","cited_by_count":19,"area":null},{"id":"2103.01454","title":"Kernel Interpolation for Scalable Online Gaussian Processes","created":"2021-03-02","cited_by_count":18,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2310.20258","title":"Advancing Bayesian Optimization via Learning Correlated Latent Space","created":"2023-10-31","cited_by_count":18,"area":null},{"id":"2312.10550","title":"Amortized Reparametrization: Efficient and Scalable Variational Inference for Latent SDEs","created":"2023-12-16","cited_by_count":18,"area":null},{"id":"2409.04538","title":"Operator Learning with Gaussian Processes","created":"2024-09-06","cited_by_count":18,"area":null},{"id":"2110.03674","title":"Dense Gaussian Processes for Few-Shot Segmentation","created":"2021-10-07","cited_by_count":17,"area":null},{"id":"2302.04228","title":"Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach","created":"2023-02-08","cited_by_count":17,"area":null},{"id":"2509.17998","title":"Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs","created":"2025-09-22","cited_by_count":17,"area":null},{"id":"2203.09179","title":"Maximum Likelihood Estimation in Gaussian Process Regression is Ill-Posed","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2303.12157","title":"Learning a Depth Covariance Function","created":"2023-03-21","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":"2202.09774","title":"Supervising the Multi-Fidelity Race of Hyperparameter Configurations","created":"2022-02-20","cited_by_count":15,"area":null},{"id":"2206.04872","title":"Multi-fidelity Hierarchical Neural Processes","created":"2022-06-10","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":"2409.20534","title":"End-to-End Conformal Calibration for Optimization Under Uncertainty","created":"2024-09-30","cited_by_count":15,"area":null},{"id":"2503.17286","title":"Offline Model-Based Optimization: Comprehensive Review","created":"2025-03-21","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":"2210.00762","title":"Meta-Learning Priors for Safe Bayesian Optimization","created":"2022-10-03","cited_by_count":14,"area":null},{"id":"2211.10381","title":"Environmental Sensor Placement with Convolutional Gaussian Neural Processes","created":"2022-11-18","cited_by_count":14,"area":null},{"id":"2302.14578","title":"Interactive Segmentation as Gaussian Process Classification","created":"2023-02-28","cited_by_count":14,"area":null},{"id":"2106.08185","title":"Kernel Identification Through Transformers","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2211.07907","title":"MMD-B-Fair: Learning Fair Representations with Statistical Testing","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2306.10915","title":"Practical Equivariances via Relational Conditional Neural Processes","created":"2023-06-19","cited_by_count":13,"area":null},{"id":"2402.18846","title":"Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling","created":"2024-02-29","cited_by_count":13,"area":null},{"id":"2504.06265","title":"Large language models as uncertainty-calibrated optimizers for experimental discovery","created":"2025-04-08","cited_by_count":13,"area":null},{"id":"2109.09690","title":"Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes","created":"2021-09-20","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":"2310.18688","title":"Clairvoyance: A Pipeline Toolkit for Medical Time Series","created":"2023-10-28","cited_by_count":12,"area":null},{"id":"2407.05375","title":"Online Drift Detection with Maximum Concept Discrepancy","created":"2024-07-07","cited_by_count":12,"area":null},{"id":"2203.01459","title":"Scalable Bayesian Optimization Using Vecchia Approximations of Gaussian Processes","created":"2022-03-02","cited_by_count":11,"area":null},{"id":"2211.07206","title":"Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice","created":"2022-11-14","cited_by_count":11,"area":null},{"id":"2310.03912","title":"RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels","created":"2023-10-05","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":"2405.03164","title":"The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning","created":"2024-05-06","cited_by_count":11,"area":null},{"id":"2411.05330","title":"Inversion-based Latent Bayesian Optimization","created":"2024-11-08","cited_by_count":11,"area":null},{"id":"2103.03945","title":"SCRIB: Set-classifier with Class-specific Risk Bounds for Blackbox Models","created":"2021-03-05","cited_by_count":10,"area":null},{"id":"2206.04287","title":"Evaluating Aleatoric Uncertainty via Conditional Generative Models","created":"2022-06-09","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":"2212.01574","title":"Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS","created":"2022-12-03","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":"2103.12045","title":"Raven's Progressive Matrices Completion with Latent Gaussian Process Priors","created":"2021-03-22","cited_by_count":9,"area":null},{"id":"2201.05319","title":"A Kernel-Expanded Stochastic Neural Network","created":"2022-01-14","cited_by_count":9,"area":null},{"id":"2304.01762","title":"Incorporating Unlabelled Data into Bayesian Neural Networks","created":"2023-04-04","cited_by_count":9,"area":null},{"id":"2305.16446","title":"The Representation Jensen-Shannon Divergence","created":"2023-05-25","cited_by_count":9,"area":null}],"next_cursor":"100"}