{"total":92,"rows":[{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239,"area":null},{"id":"2205.15902","title":"Variational inference via Wasserstein gradient flows","created":"2022-05-31","cited_by_count":85,"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":"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":"2111.10510","title":"Bayesian Learning via Neural Schr\\\"odinger-F\\\"ollmer Flows","created":"2021-11-20","cited_by_count":56,"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":"2210.01620","title":"SAM as an Optimal Relaxation of Bayes","created":"2022-10-04","cited_by_count":41,"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":"2405.05646","title":"Outlier-robust Kalman Filtering through Generalised Bayes","created":"2024-05-09","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":"2310.19273","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","created":"2023-10-30","cited_by_count":16,"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":"2208.13723","title":"Bayesian Continual Learning via Spiking Neural Networks","created":"2022-08-29","cited_by_count":13,"area":null},{"id":"2307.07785","title":"The Interpolating Information Criterion for Overparameterized Models","created":"2023-07-15","cited_by_count":12,"area":null},{"id":"2112.02880","title":"AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks","created":"2021-12-06","cited_by_count":11,"area":null},{"id":"2306.03566","title":"Memory-Based Dual Gaussian Processes for Sequential Learning","created":"2023-06-06","cited_by_count":11,"area":null},{"id":"2503.05318","title":"Uncertainty-Aware Decoding with Minimum Bayes Risk","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2210.03512","title":"Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes","created":"2022-10-07","cited_by_count":10,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","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":"2504.13569","title":"Bayesian continual learning and forgetting in neural networks","created":"2025-04-18","cited_by_count":9,"area":null},{"id":"2202.06236","title":"Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems","created":"2022-02-13","cited_by_count":7,"area":null},{"id":"2211.01053","title":"Fantasizing with Dual GPs in Bayesian Optimization and Active Learning","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2403.01371","title":"eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling","created":"2024-03-03","cited_by_count":7,"area":null},{"id":"2501.17049","title":"Hellinger-Kantorovich Gradient Flows: Global Exponential Decay of Entropy Functionals","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2506.14262","title":"Knowledge Adaptation as Posterior Correction","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2206.12361","title":"Robustness to corruption in pre-trained Bayesian neural networks","created":"2022-06-24","cited_by_count":5,"area":null},{"id":"2310.01951","title":"Probabilistic Reach-Avoid for Bayesian Neural Networks","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2411.10153","title":"A unifying framework for generalised Bayesian online learning in non-stationary environments","created":"2024-11-15","cited_by_count":5,"area":null},{"id":"2506.17796","title":"SING: SDE Inference via Natural Gradients","created":"2025-06-21","cited_by_count":5,"area":null},{"id":"2110.04996","title":"A Survey of Learning Criteria Going Beyond the Usual Risk","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2311.10580","title":"Implicit Maximum a Posteriori Filtering via Adaptive Optimization","created":"2023-11-17","cited_by_count":4,"area":null},{"id":"2411.00214","title":"Inclusive KL Gradient Flows: Otto-Wasserstein, Fisher-Rao-Gaussian, and Local-Estimator Dynamics","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2501.17325","title":"Connecting Federated ADMM to Bayes","created":"2025-01-28","cited_by_count":4,"area":null},{"id":"2506.11898","title":"Martingale Posterior Neural Networks for Fast Sequential Decision Making","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2509.24894","title":"Improved Stochastic Optimization of LogSumExp","created":"2025-09-29","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":"2202.13932","title":"Leveraging Channel Noise for Sampling and Privacy via Quantized Federated Langevin Monte Carlo","created":"2022-02-28","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":"2302.01302","title":"Bayesian Inference on Binary Spiking Networks Leveraging Nanoscale Device Stochasticity","created":"2023-02-02","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":"2501.06066","title":"Distilling Calibration via Conformalized Credal Inference","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2506.13150","title":"Federated ADMM from Bayesian Duality","created":"2025-06-16","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":"2211.03741","title":"AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2405.18351","title":"Evaluating Bayesian deep learning for radio galaxy classification","created":"2024-05-28","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":"2507.07288","title":"Natural Evolutionary Search meets Probabilistic Numerics","created":"2025-07-09","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":"2509.23162","title":"Dense associative memory for Gaussian distributions","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2203.02720","title":"Bayesian Learning Approach to Model Predictive Control","created":"2022-03-05","cited_by_count":1,"area":null},{"id":"2304.14251","title":"Variational Bayes Made Easy","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2312.01227","title":"Distributed Bayesian Estimation in Sensor Networks: Consensus on Marginal Densities","created":"2023-12-02","cited_by_count":1,"area":null},{"id":"2312.09585","title":"Joint State Estimation and Noise Identification Based on Variational Optimization","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2412.08147","title":"Variational Model Merging for Pareto Front Estimation in Multitask Finetuning","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2502.10295","title":"Fenchel-Young Variational Learning","created":"2025-02-14","cited_by_count":1,"area":null},{"id":"2506.09648","title":"Scaling Laws for Uncertainty in Deep Learning","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2507.20272","title":"Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2511.21223","title":"Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.18420","title":"Gradient Regularized Natural Gradients","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2604.00683","title":"Convergence of projected stochastic natural gradient variational inference for various step size and sample or batch size schedules","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.29467","title":"Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2608.09805","title":"Parameter Exploration for RLVR via Variational Learning","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2208.13898","title":"Conjugate Natural Selection","created":"2022-08-29","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":"2410.14390","title":"Personalizing Low-Rank Bayesian Neural Networks Via Federated Learning","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2411.07902","title":"Bayes2IMC: In-Memory Computing for Bayesian Binary Neural Networks","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2411.18788","title":"Investigating Plausibility of Biologically Inspired Bayesian Learning in ANNs","created":"2024-11-27","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":"2502.21143","title":"Variational Bayesian Pseudo-Coreset","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2503.18608","title":"AutoBayes: A Compositional Framework for Generalized Variational Inference","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2509.10132","title":"Cost-Free Personalization via Information-Geometric Projection in Bayesian Federated Learning","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2512.01930","title":"SVRG and Beyond via Posterior Correction","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2602.10602","title":"Learning Mixture Density via Natural Gradient Expectation Maximization","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.18718","title":"Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2604.08624","title":"Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.03134","title":"Bayesian inference with sources of uncertainty: from confidence modelling to sparse estimation","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.29908","title":"Joint Model and Data Sparsification via the Marginal Likelihood","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30198","title":"Active Continual Learning with Metaplastic Binary Bayesian Neural Networks","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.31163","title":"Memory by Design: Bayesian Layers for Sequence Modeling","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.07841","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.24007","title":"Fast and Slow Variational Continual Learning","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.15922","title":"Information Geometry of Message Passing","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.25706","title":"Fast rates in Bayesian online learning with approximate posteriors","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.09126","title":"A Generalization of Amari's Bayesian Duality","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.15289","title":"Math for AI safety: an invitation for mathematicians","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.31107","title":"Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.31559","title":"Online Learning via Learned Latent Bayesian Tracking","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}