{"total":94,"rows":[{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680,"area":null},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308,"area":null},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106,"area":null},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101,"area":null},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2205.15902","title":"Variational inference via Wasserstein gradient flows","created":"2022-05-31","cited_by_count":85,"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":"2402.17641","title":"Variational Learning is Effective for Large Deep Networks","created":"2024-02-27","cited_by_count":65,"area":null},{"id":"2107.00649","title":"On the Practicality of Deterministic Epistemic Uncertainty","created":"2021-07-01","cited_by_count":62,"area":null},{"id":"2304.08151","title":"Prediction-Oriented Bayesian Active Learning","created":"2023-04-17","cited_by_count":62,"area":null},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"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":"2102.06559","title":"Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations","created":"2021-02-12","cited_by_count":38,"area":null},{"id":"2106.05586","title":"Data augmentation in Bayesian neural networks and the cold posterior effect","created":"2021-06-10","cited_by_count":36,"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":"2304.05398","title":"Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein Space","created":"2023-04-10","cited_by_count":36,"area":null},{"id":"2310.11142","title":"BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference","created":"2023-10-17","cited_by_count":35,"area":"diffusion"},{"id":"2302.05086","title":"Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples","created":"2023-02-10","cited_by_count":32,"area":null},{"id":"2201.12250","title":"Gradient Descent on Neurons and its Link to Approximate Second-Order Optimization","created":"2022-01-28","cited_by_count":30,"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":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2102.05289","title":"Bayesian Inference with Certifiable Adversarial Robustness","created":"2021-02-10","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":"2402.03496","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","created":"2024-02-05","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":"2102.07405","title":"Tractable structured natural gradient descent using local parameterizations","created":"2021-02-15","cited_by_count":22,"area":null},{"id":"2204.02738","title":"Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network","created":"2022-04-06","cited_by_count":21,"area":null},{"id":"2305.04684","title":"ASDL: A Unified Interface for Gradient Preconditioning in PyTorch","created":"2023-05-08","cited_by_count":21,"area":null},{"id":"2107.01739","title":"KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks","created":"2021-07-04","cited_by_count":20,"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":"2105.14594","title":"Sparse Uncertainty Representation in Deep Learning with Inducing Weights","created":"2021-05-30","cited_by_count":16,"area":null},{"id":"2106.10065","title":"Being a Bit Frequentist Improves Bayesian Neural Networks","created":"2021-06-18","cited_by_count":15,"area":null},{"id":"2310.19272","title":"NPCL: Neural Processes for Uncertainty-Aware Continual Learning","created":"2023-10-30","cited_by_count":14,"area":null},{"id":"2406.00104","title":"Scalable Bayesian Learning with posteriors","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2207.06154","title":"On the Robustness of Bayesian Neural Networks to Adversarial Attacks","created":"2022-07-13","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":"2409.12661","title":"Manifold Sampling for Differentiable Uncertainty in Radiance Fields","created":"2024-09-19","cited_by_count":12,"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":"2106.06245","title":"Model Selection for Bayesian Autoencoders","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2206.15078","title":"Laplacian Autoencoders for Learning Stochastic Representations","created":"2022-06-30","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":"2505.19371","title":"Foundations of Top-$k$ Decoding For Language Models","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2211.07725","title":"Hierarchically Structured Task-Agnostic Continual Learning","created":"2022-11-14","cited_by_count":9,"area":null},{"id":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2406.15972","title":"EVCL: Elastic Variational Continual Learning with Weight Consolidation","created":"2024-06-23","cited_by_count":9,"area":null},{"id":"2105.13688","title":"Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving","created":"2021-05-28","cited_by_count":8,"area":null},{"id":"2110.12667","title":"Mixture-of-Variational-Experts for Continual Learning","created":"2021-10-25","cited_by_count":8,"area":null},{"id":"2306.10742","title":"BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming","created":"2023-06-19","cited_by_count":8,"area":null},{"id":"2406.01870","title":"Understanding Stochastic Natural Gradient Variational Inference","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2102.07927","title":"Structured Dropout Variational Inference for Bayesian Neural Networks","created":"2021-02-16","cited_by_count":7,"area":null},{"id":"2306.13614","title":"Adversarial Robustness Certification for Bayesian Neural Networks","created":"2023-06-23","cited_by_count":7,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2404.08981","title":"Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification","created":"2024-04-13","cited_by_count":6,"area":null},{"id":"2207.03859","title":"Variational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical study","created":"2022-07-08","cited_by_count":5,"area":null},{"id":"2410.04196","title":"Improving Generalization with Flat Hilbert Bayesian Inference","created":"2024-10-05","cited_by_count":5,"area":null},{"id":"2105.09095","title":"Aleatoric uncertainty for Errors-in-Variables models in deep regression","created":"2021-05-19","cited_by_count":4,"area":null},{"id":"2111.08591","title":"Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks","created":"2021-11-16","cited_by_count":4,"area":null},{"id":"2205.03109","title":"Controlled Dropout for Uncertainty Estimation","created":"2022-05-06","cited_by_count":4,"area":null},{"id":"2303.04012","title":"Exploration via Epistemic Value Estimation","created":"2023-03-07","cited_by_count":4,"area":null},{"id":"2307.11334","title":"Improving Transferability of Adversarial Examples via Bayesian Attacks","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2407.18707","title":"Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2510.19163","title":"Natural Gradient VI: Guarantees for Non-Conjugate Models","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2603.09453","title":"Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers","created":"2026-03-10","cited_by_count":3,"area":"moe"},{"id":"2605.00742","title":"Position: agentic AI orchestration should be Bayes-consistent","created":"2026-05-01","cited_by_count":3,"area":"agents"},{"id":"2105.08620","title":"Adversarial Examples Detection with Bayesian Neural Network","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2210.12957","title":"On the optimization and pruning for Bayesian deep learning","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2310.14963","title":"Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens","created":"2023-10-23","cited_by_count":2,"area":null},{"id":"2502.01861","title":"Learning Hyperparameters via a Data-Emphasized Variational Objective","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2011.14266","title":"Distilled Thompson Sampling: Practical and Efficient Thompson Sampling via Imitation Learning","created":"2020-11-29","cited_by_count":1,"area":"offlinerl"},{"id":"2101.06608","title":"Network Automatic Pruning: Start NAP and Take a Nap","created":"2021-01-17","cited_by_count":1,"area":null},{"id":"2103.15041","title":"Accurate and Reliable Forecasting using Stochastic Differential Equations","created":"2021-03-28","cited_by_count":1,"area":null},{"id":"2205.00163","title":"Deep Ensemble as a Gaussian Process Approximate Posterior","created":"2022-04-30","cited_by_count":1,"area":null},{"id":"2210.14598","title":"Manifold Gaussian Variational Bayes on the Precision Matrix","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2211.06139","title":"Understanding Approximation for Bayesian Inference in Neural Networks","created":"2022-11-11","cited_by_count":1,"area":null},{"id":"2211.06457","title":"The Implicit Delta Method","created":"2022-11-11","cited_by_count":1,"area":null},{"id":"2302.06035","title":"Variational Bayesian Neural Networks via Resolution of Singularities","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2507.14652","title":"Accelerating Hamiltonian Monte Carlo for Bayesian Inference in Neural Networks and Neural Operators","created":"2025-07-19","cited_by_count":1,"area":null},{"id":"2302.13536","title":"Natural Gradient Hybrid Variational Inference with Application to Deep Mixed Models","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2303.18083","title":"Analysis and Comparison of Two-Level KFAC Methods for Training Deep Neural Networks","created":"2023-03-31","cited_by_count":0,"area":null},{"id":"2306.13914","title":"G-TRACER: Expected Sharpness Optimization","created":"2023-06-24","cited_by_count":0,"area":null},{"id":"2307.06055","title":"Function-Space Regularization for Deep Bayesian Classification","created":"2023-07-12","cited_by_count":0,"area":null},{"id":"2308.06293","title":"Target Detection on Hyperspectral Images Using MCMC and VI Trained Bayesian Neural Networks","created":"2023-08-11","cited_by_count":0,"area":null},{"id":"2309.04742","title":"Affine Invariant Ensemble Transform Methods to Improve Predictive Uncertainty in Neural Networks","created":"2023-09-09","cited_by_count":0,"area":null},{"id":"2309.11378","title":"Preconditioned Federated Learning","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2403.15432","title":"BRIEDGE: EEG-Adaptive Edge AI for Multi-Brain to Multi-Robot Interaction","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2405.13535","title":"Addressing the Inconsistency in Bayesian Deep Learning via Generalized Laplace Approximation","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2502.06268","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2502.07273","title":"Variational Learning Induces Adaptive Label Smoothing","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2505.20235","title":"Variational Deep Learning via Implicit Regularization","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2602.21948","title":"Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesis","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2602.21965","title":"Compact Circulant Layers with Spectral Priors","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2602.23219","title":"Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime","created":"2026-02-26","cited_by_count":0,"area":null}],"next_cursor":null}