{"total":320,"rows":[{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"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":"2103.04715","title":"Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie","created":"2021-03-08","cited_by_count":97,"area":null},{"id":"2305.17535","title":"PFNs4BO: In-Context Learning for Bayesian Optimization","created":"2023-05-27","cited_by_count":73,"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":"2310.02679","title":"Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization","created":"2023-10-04","cited_by_count":57,"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":"2207.06211","title":"Sample-dependent Adaptive Temperature Scaling for Improved Calibration","created":"2022-07-13","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":"2205.10279","title":"Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors","created":"2022-05-20","cited_by_count":43,"area":null},{"id":"2110.04840","title":"Heavy Ball Neural Ordinary Differential Equations","created":"2021-10-10","cited_by_count":42,"area":null},{"id":"2107.04150","title":"MCMC Variational Inference via Uncorrected Hamiltonian Annealing","created":"2021-07-08","cited_by_count":39,"area":null},{"id":"2106.05863","title":"Learning Functional Priors and Posteriors from Data and Physics","created":"2021-06-08","cited_by_count":37,"area":null},{"id":"2107.10211","title":"Differentiable Annealed Importance Sampling and the Perils of Gradient Noise","created":"2021-07-21","cited_by_count":36,"area":null},{"id":"2307.13917","title":"BayesDAG: Gradient-Based Posterior Inference for Causal Discovery","created":"2023-07-26","cited_by_count":33,"area":null},{"id":"2207.07256","title":"Improving Task-free Continual Learning by Distributionally Robust Memory Evolution","created":"2022-07-15","cited_by_count":31,"area":null},{"id":"2102.01691","title":"Exact Langevin Dynamics with Stochastic Gradients","created":"2021-02-02","cited_by_count":30,"area":null},{"id":"2202.07176","title":"DeepONet-Grid-UQ: A Trustworthy Deep Operator Framework for Predicting the Power Grid's Post-Fault Trajectories","created":"2022-02-15","cited_by_count":30,"area":null},{"id":"2206.08900","title":"Adapting the Linearised Laplace Model Evidence for Modern Deep Learning","created":"2022-06-17","cited_by_count":29,"area":null},{"id":"2212.03281","title":"Copula Conformal Prediction for Multi-step Time Series Forecasting","created":"2022-12-06","cited_by_count":29,"area":null},{"id":"2210.12642","title":"Accelerated Linearized Laplace Approximation for Bayesian Deep Learning","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2307.03217","title":"Quantification of Uncertainty with Adversarial Models","created":"2023-07-06","cited_by_count":28,"area":null},{"id":"2402.15406","title":"Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks","created":"2024-02-23","cited_by_count":28,"area":null},{"id":"2206.14502","title":"RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness","created":"2022-06-29","cited_by_count":27,"area":null},{"id":"2212.00790","title":"Sparsity Agnostic Depth Completion","created":"2022-12-01","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":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","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":"2206.01665","title":"BaCaDI: Bayesian Causal Discovery with Unknown Interventions","created":"2022-06-03","cited_by_count":26,"area":null},{"id":"2205.09940","title":"Conformal Prediction with Temporal Quantile Adjustments","created":"2022-05-20","cited_by_count":25,"area":null},{"id":"2111.01968","title":"A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications","created":"2021-11-03","cited_by_count":24,"area":null},{"id":"2206.00050","title":"FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation","created":"2022-05-31","cited_by_count":24,"area":null},{"id":"2211.10575","title":"Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants","created":"2022-11-19","cited_by_count":24,"area":null},{"id":"2207.06873","title":"BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2106.06596","title":"Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect","created":"2021-06-11","cited_by_count":22,"area":null},{"id":"2111.02484","title":"Accelerated replica exchange stochastic gradient Langevin diffusion enhanced Bayesian DeepONet for solving noisy parametric PDEs","created":"2021-11-03","cited_by_count":22,"area":null},{"id":"2412.16577","title":"A Meta-Learning Approach to Bayesian Causal Discovery","created":"2024-12-21","cited_by_count":22,"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":"2208.09282","title":"Diagnose Like a Radiologist: Hybrid Neuro-Probabilistic Reasoning for Attribute-Based Medical Image Diagnosis","created":"2022-08-19","cited_by_count":21,"area":null},{"id":"2211.13954","title":"Particle-based Variational Inference with Preconditioned Functional Gradient Flow","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2405.14438","title":"LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks","created":"2024-05-23","cited_by_count":20,"area":null},{"id":"2302.12565","title":"Variational Linearized Laplace Approximation for Bayesian Deep Learning","created":"2023-02-24","cited_by_count":18,"area":null},{"id":"2201.10035","title":"Maximizing information from chemical engineering data sets: Applications to machine learning","created":"2022-01-25","cited_by_count":17,"area":null},{"id":"2102.07542","title":"High-Dimensional Gaussian Process Inference with Derivatives","created":"2021-02-15","cited_by_count":16,"area":null},{"id":"2312.04836","title":"Thermodynamic Computing System for AI Applications","created":"2023-12-08","cited_by_count":16,"area":null},{"id":"2410.10786","title":"On Information-Theoretic Measures of Predictive Uncertainty","created":"2024-10-14","cited_by_count":16,"area":null},{"id":"2302.06584","title":"Thermodynamic AI and the fluctuation frontier","created":"2023-02-09","cited_by_count":15,"area":null},{"id":"2112.05120","title":"On Convergence of Federated Averaging Langevin Dynamics","created":"2021-12-09","cited_by_count":14,"area":null},{"id":"2112.12194","title":"Surrogate Likelihoods for Variational Annealed Importance Sampling","created":"2021-12-22","cited_by_count":14,"area":null},{"id":"2302.04019","title":"Fortuna: A Library for Uncertainty Quantification in Deep Learning","created":"2023-02-08","cited_by_count":14,"area":null},{"id":"2503.10148","title":"3D Student Splatting and Scooping","created":"2025-03-13","cited_by_count":14,"area":null},{"id":"2106.12135","title":"Deep Gaussian Processes: A Survey","created":"2021-06-21","cited_by_count":13,"area":null},{"id":"2110.04020","title":"Pathologies in priors and inference for Bayesian transformers","created":"2021-10-08","cited_by_count":13,"area":null},{"id":"2205.08187","title":"Deep neural networks with dependent weights: Gaussian Process mixture limit, heavy tails, sparsity and compressibility","created":"2022-05-17","cited_by_count":13,"area":null},{"id":"2406.00104","title":"Scalable Bayesian Learning with posteriors","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2410.19780","title":"Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2107.09028","title":"Structured Stochastic Gradient MCMC","created":"2021-07-19","cited_by_count":12,"area":null},{"id":"2206.09909","title":"Low-Precision Stochastic Gradient Langevin Dynamics","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2310.08287","title":"A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors","created":"2023-10-12","cited_by_count":12,"area":null},{"id":"2311.01046","title":"Time-Independent Information-Theoretic Generalization Bounds for SGLD","created":"2023-11-02","cited_by_count":12,"area":null},{"id":"2405.16475","title":"Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models","created":"2024-05-26","cited_by_count":12,"area":null},{"id":"2105.13059","title":"Efficient and Generalizable Tuning Strategies for Stochastic Gradient MCMC","created":"2021-05-27","cited_by_count":11,"area":null},{"id":"2209.03580","title":"Conformal Methods for Quantifying Uncertainty in Spatiotemporal Data: A Survey","created":"2022-09-08","cited_by_count":11,"area":null},{"id":"2212.07959","title":"Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls","created":"2022-12-15","cited_by_count":11,"area":null},{"id":"2308.10544","title":"Towards Accelerated Model Training via Bayesian Data Selection","created":"2023-08-21","cited_by_count":11,"area":null},{"id":"2309.10852","title":"Using AI Uncertainty Quantification to Improve Human Decision-Making","created":"2023-09-19","cited_by_count":11,"area":null},{"id":"2106.06245","title":"Model Selection for Bayesian Autoencoders","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2210.04349","title":"Nonlinear Sufficient Dimension Reduction with a Stochastic Neural Network","created":"2022-10-09","cited_by_count":10,"area":null},{"id":"2210.06205","title":"On Divergence Measures for Bayesian Pseudocoresets","created":"2022-10-12","cited_by_count":10,"area":null},{"id":"2302.02713","title":"Flat Seeking Bayesian Neural Networks","created":"2023-02-06","cited_by_count":10,"area":null},{"id":"2305.13849","title":"Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2310.16516","title":"Particle-based Variational Inference with Generalized Wasserstein Gradient Flow","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2401.11665","title":"Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo","created":"2024-01-22","cited_by_count":10,"area":null},{"id":"2404.10124","title":"Epistemic Uncertainty Quantification For Pre-trained Neural Network","created":"2024-04-15","cited_by_count":10,"area":null},{"id":"2106.06997","title":"Post-hoc loss-calibration for Bayesian neural networks","created":"2021-06-13","cited_by_count":9,"area":null},{"id":"2111.13154","title":"Country-wide Retrieval of Forest Structure From Optical and SAR Satellite Imagery With Deep Ensembles","created":"2021-11-25","cited_by_count":9,"area":null},{"id":"2202.09867","title":"Interacting Contour Stochastic Gradient Langevin Dynamics","created":"2022-02-20","cited_by_count":9,"area":null},{"id":"2203.04713","title":"Defending Black-box Skeleton-based Human Activity Classifiers","created":"2022-03-09","cited_by_count":9,"area":null},{"id":"2205.12940","title":"Conformal Prediction Intervals with Temporal Dependence","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2301.07609","title":"Physics-informed Information Field Theory for Modeling Physical Systems with Uncertainty Quantification","created":"2023-01-18","cited_by_count":9,"area":null},{"id":"2302.04534","title":"Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes","created":"2023-02-09","cited_by_count":9,"area":null},{"id":"2305.14765","title":"Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2312.16429","title":"GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework","created":"2023-12-27","cited_by_count":9,"area":null},{"id":"2403.12729","title":"Posterior Uncertainty Quantification in Neural Networks using Data Augmentation","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2102.11062","title":"On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks","created":"2021-02-22","cited_by_count":8,"area":null},{"id":"2108.12107","title":"An Introduction to Hamiltonian Monte Carlo Method for Sampling","created":"2021-08-27","cited_by_count":8,"area":null},{"id":"2303.05101","title":"Scalable Stochastic Gradient Riemannian Langevin Dynamics in Non-Diagonal Metrics","created":"2023-03-09","cited_by_count":8,"area":null},{"id":"2304.04824","title":"Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning","created":"2023-04-10","cited_by_count":8,"area":null},{"id":"2308.00799","title":"Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction","created":"2023-08-01","cited_by_count":8,"area":null},{"id":"2402.13410","title":"Bayesian Neural Networks with Domain Knowledge Priors","created":"2024-02-20","cited_by_count":8,"area":null},{"id":"2101.06417","title":"Bayesian Inference Forgetting","created":"2021-01-16","cited_by_count":7,"area":null},{"id":"2110.00653","title":"Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration","created":"2021-10-01","cited_by_count":7,"area":null},{"id":"2206.00241","title":"Asymptotic Properties for Bayesian Neural Network in Besov Space","created":"2022-06-01","cited_by_count":7,"area":null},{"id":"2207.02189","title":"Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time","created":"2022-07-05","cited_by_count":7,"area":null},{"id":"2211.10837","title":"Non-reversible Parallel Tempering for Deep Posterior Approximation","created":"2022-11-20","cited_by_count":7,"area":null},{"id":"2302.09921","title":"Free-Form Variational Inference for Gaussian Process State-Space Models","created":"2023-02-20","cited_by_count":7,"area":null},{"id":"2311.15587","title":"Quantum Langevin Dynamics for Optimization","created":"2023-11-27","cited_by_count":7,"area":null},{"id":"2402.11025","title":"Training Bayesian Neural Networks with Sparse Subspace Variational Inference","created":"2024-02-16","cited_by_count":7,"area":null},{"id":"2602.06500","title":"Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?","created":"2026-02-06","cited_by_count":7,"area":null}],"next_cursor":"100"}