{"total":125,"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":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84,"area":null},{"id":"2310.12808","title":"Model Merging by Uncertainty-Based Gradient Matching","created":"2023-10-19","cited_by_count":77,"area":null},{"id":"2110.04593","title":"Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning","created":"2021-10-09","cited_by_count":72,"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":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"area":null},{"id":"2304.14647","title":"An Adaptive Policy to Employ Sharpness-Aware Minimization","created":"2023-04-28","cited_by_count":43,"area":null},{"id":"2210.01620","title":"SAM as an Optimal Relaxation of Bayes","created":"2022-10-04","cited_by_count":41,"area":null},{"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":"2211.11865","title":"Bayesian Learning for Neural Networks: an algorithmic survey","created":"2022-11-21","cited_by_count":23,"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":"2209.11533","title":"A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models","created":"2022-09-23","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":"2305.04684","title":"ASDL: A Unified Interface for Gradient Preconditioning in PyTorch","created":"2023-05-08","cited_by_count":21,"area":null},{"id":"2306.12306","title":"Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift","created":"2023-06-21","cited_by_count":20,"area":null},{"id":"2405.03425","title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models","created":"2024-05-06","cited_by_count":20,"area":null},{"id":"2111.03412","title":"Dual Parameterization of Sparse Variational Gaussian Processes","created":"2021-11-05","cited_by_count":19,"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":"2209.10888","title":"Amortized Variational Inference: A Systematic Review","created":"2022-09-22","cited_by_count":16,"area":null},{"id":"2302.11024","title":"Gradient Flows for Sampling: Mean-Field Models, Gaussian Approximations and Affine Invariance","created":"2023-02-21","cited_by_count":16,"area":null},{"id":"2310.19273","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","created":"2023-10-30","cited_by_count":16,"area":null},{"id":"2305.16905","title":"Improving Neural Additive Models with Bayesian Principles","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2306.07158","title":"Riemannian Laplace approximations for Bayesian neural networks","created":"2023-06-12","cited_by_count":15,"area":null},{"id":"2405.19681","title":"Bayesian Online Natural Gradient (BONG)","created":"2024-05-30","cited_by_count":14,"area":null},{"id":"2111.01721","title":"Bayes-Newton Methods for Approximate Bayesian Inference with PSD Guarantees","created":"2021-11-02","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":"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":"2412.05723","title":"Training-Free Bayesianization for Low-Rank Adapters of Large Language Models","created":"2024-12-07","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":"2302.02713","title":"Flat Seeking Bayesian Neural Networks","created":"2023-02-06","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":"2305.04557","title":"Toward Adversarial Training on Contextualized Language Representation","created":"2023-05-08","cited_by_count":10,"area":null},{"id":"2206.07673","title":"Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling","created":"2022-06-15","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":"2105.10134","title":"Certification of Iterative Predictions in Bayesian Neural Networks","created":"2021-05-21","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":"2403.10929","title":"Function-space Parameterization of Neural Networks for Sequential Learning","created":"2024-03-16","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":"2503.01595","title":"STAR: Stability-Inducing Weight Perturbation for Continual Learning","created":"2025-03-03","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":"2107.10884","title":"Structured second-order methods via natural gradient descent","created":"2021-07-22","cited_by_count":7,"area":null},{"id":"2206.08640","title":"Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift","created":"2022-06-17","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":"2210.13983","title":"Optimization for Amortized Inverse Problems","created":"2022-10-25","cited_by_count":6,"area":null},{"id":"2111.13204","title":"BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule","created":"2021-11-25","cited_by_count":5,"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":"2311.10945","title":"An Empirical Bayes Framework for Open-Domain Dialogue Generation","created":"2023-11-18","cited_by_count":5,"area":null},{"id":"2403.07282","title":"Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2112.15362","title":"Modeling Mask Uncertainty in Hyperspectral Image Reconstruction","created":"2021-12-31","cited_by_count":4,"area":null},{"id":"2405.17164","title":"WeiPer: OOD Detection using Weight Perturbations of Class Projections","created":"2024-05-27","cited_by_count":4,"area":null},{"id":"2510.26997","title":"Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2201.12724","title":"Stochastic Neural Networks with Infinite Width are Deterministic","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2205.11568","title":"Quasi Black-Box Variational Inference with Natural Gradients for Bayesian Learning","created":"2022-05-23","cited_by_count":3,"area":null},{"id":"2206.11173","title":"Cold Posteriors through PAC-Bayes","created":"2022-06-22","cited_by_count":3,"area":null},{"id":"2210.06436","title":"Deep Combinatorial Aggregation","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2303.04397","title":"The Lie-Group Bayesian Learning Rule","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2304.10828","title":"Individual Fairness in Bayesian Neural Networks","created":"2023-04-21","cited_by_count":3,"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":"2410.16901","title":"Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2412.05169","title":"Towards Understanding the Role of Sharpness-Aware Minimization Algorithms for Out-of-Distribution Generalization","created":"2024-12-06","cited_by_count":3,"area":null},{"id":"2505.11412","title":"Uncertainty quantification with approximate variational learning for wearable photoplethysmography prediction tasks","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2507.07853","title":"Optimization Guarantees for Square-Root Natural-Gradient Variational Inference","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2606.23357","title":"SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2103.08497","title":"Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise","created":"2021-03-15","cited_by_count":2,"area":null},{"id":"2109.10888","title":"A Physics inspired Functional Operator for Model Uncertainty Quantification in the RKHS","created":"2021-09-22","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":"2211.01999","title":"Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS","created":"2022-11-03","cited_by_count":2,"area":null},{"id":"2407.02721","title":"Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning","created":"2024-07-03","cited_by_count":2,"area":null},{"id":"2411.18385","title":"Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2506.12903","title":"Variational Learning Finds Flatter Solutions at the Edge of Stability","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2506.17768","title":"Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2509.15641","title":"Information Geometry of Variational Bayes","created":"2025-09-19","cited_by_count":2,"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":"2111.08002","title":"Natural Gradient Variational Inference with Gaussian Mixture Models","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2112.06281","title":"Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer","created":"2021-12-12","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":"2207.12131","title":"Complementing Semi-Supervised Learning with Uncertainty Quantification","created":"2022-07-22","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":"2302.06035","title":"Variational Bayesian Neural Networks via Resolution of Singularities","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2307.04779","title":"Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference","created":"2023-07-10","cited_by_count":1,"area":null},{"id":"2309.08546","title":"Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2309.12095","title":"Bayesian sparsification for deep neural networks with Bayesian model reduction","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.11837","title":"Optimising Distributions with Natural Gradient Surrogates","created":"2023-10-18","cited_by_count":1,"area":null},{"id":"2311.09639","title":"On the Quantification of Image Reconstruction Uncertainty without Training Data","created":"2023-11-16","cited_by_count":1,"area":null},{"id":"2406.15664","title":"Flat Posterior Does Matter For Bayesian Model Averaging","created":"2024-06-21","cited_by_count":1,"area":null},{"id":"2408.08222","title":"Enhancing Sharpness-Aware Minimization by Learning Perturbation Radius","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2408.13689","title":"Decentralised Variational Inference Frameworks for Multi-object Tracking on Sensor Networks: Additional Notes","created":"2024-08-24","cited_by_count":1,"area":null}],"next_cursor":"100"}