{"list":"other","total":57,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","cited_by_count":389},{"id":"1810.09538","title":"Pyro: Deep Universal Probabilistic Programming","created":"2018-10-18","cited_by_count":380},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1402.4102","title":"Stochastic Gradient Hamiltonian Monte Carlo","created":"2014-02-17","cited_by_count":343},{"id":"1710.10628","title":"Variational Continual Learning","created":"2017-10-29","cited_by_count":339},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent","created":"2019-05-29","cited_by_count":217},{"id":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"1912.11554","title":"Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro","created":"2019-12-24","cited_by_count":191},{"id":"1506.04696","title":"A Complete Recipe for Stochastic Gradient MCMC","created":"2015-06-15","cited_by_count":146},{"id":"1602.01407","title":"A Kronecker-factored approximate Fisher matrix for convolution layers","created":"2016-02-03","cited_by_count":141},{"id":"2209.03302","title":"Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?","created":"2022-09-07","cited_by_count":125},{"id":"1512.07666","title":"Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks","created":"2015-12-23","cited_by_count":121},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101},{"id":"1703.09194","title":"Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference","created":"2017-03-27","cited_by_count":98},{"id":"1506.03039","title":"Measuring Sample Quality with Stein's Method","created":"2015-06-09","cited_by_count":94},{"id":"1712.02390","title":"Noisy Natural Gradient as Variational Inference","created":"2017-12-06","cited_by_count":94},{"id":"1906.11537","title":"'In-Between' Uncertainty in Bayesian Neural Networks","created":"2019-06-27","cited_by_count":80},{"id":"2404.11599","title":"Variational Bayesian Last Layers","created":"2024-04-17","cited_by_count":69},{"id":"1907.06986","title":"Stochastic gradient Markov chain Monte Carlo","created":"2019-07-16","cited_by_count":56},{"id":"1712.03847","title":"On Quadratic Penalties in Elastic Weight Consolidation","created":"2017-12-11","cited_by_count":55},{"id":"2008.05912","title":"A statistical theory of cold posteriors in deep neural networks","created":"2020-08-13","cited_by_count":54},{"id":"2011.01808","title":"Bayesian Workflow","created":"2020-11-03","cited_by_count":49},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49},{"id":"2312.00995","title":"Second-Order Uncertainty Quantification: A Distance-Based Approach","created":"2023-12-02","cited_by_count":35},{"id":"1703.00209","title":"Online Natural Gradient as a Kalman Filter","created":"2017-03-01","cited_by_count":25},{"id":"2404.12215","title":"Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rules","created":"2024-04-18","cited_by_count":21},{"id":"1607.03954","title":"Ensemble preconditioning for Markov chain Monte Carlo simulation","created":"2016-07-13","cited_by_count":16},{"id":"2112.00195","title":"Efficient Online Bayesian Inference for Neural Bandits","created":"2021-12-01","cited_by_count":15},{"id":"2302.04019","title":"Fortuna: A Library for Uncertainty Quantification in Deep Learning","created":"2023-02-08","cited_by_count":14},{"id":"2305.14442","title":"Optimal Preconditioning and Fisher Adaptive Langevin Sampling","created":"2023-05-23","cited_by_count":14},{"id":"2107.09028","title":"Structured Stochastic Gradient MCMC","created":"2021-07-19","cited_by_count":12},{"id":"2110.13017","title":"Nested $\\hat R$: Assessing the convergence of Markov chain Monte Carlo when running many short chains","created":"2021-10-25","cited_by_count":9},{"id":"2310.07002","title":"Bayesian cross-validation by parallel Markov Chain Monte Carlo","created":"2023-10-10","cited_by_count":3},{"id":"2308.02414","title":"A State-Space Perspective on Modelling and Inference for Online Skill Rating","created":"2023-08-04","cited_by_count":2},{"id":"2312.14027","title":"AdamMCMC: Combining Metropolis Adjusted Langevin with Momentum-based Optimization","created":"2023-12-21","cited_by_count":2},{"id":"2211.12580","title":"Quasi-Newton Sequential Monte Carlo","created":"2022-11-22","cited_by_count":1}],"next_cursor":null}