Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks von Kristiadi, Agustinus, Eschenhagen, Runa, Hennig, Philipp

Volltext bestellen

Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization von Kristiadi, Agustinus, Immer, Alexander, Eschenhagen, Runa, Fortuin, Vincent

Volltext bestellen

Influence Functions for Scalable Data Attribution in Diffusion Models von Mlodozeniec, Bruno, Eschenhagen, Runa, Bae, Juhan, Immer, Alexander, Krueger, David, Turner, Richard

Volltext bestellen

Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs von Magnani, Emilia, Krämer, Nicholas, Eschenhagen, Runa, Rosasco, Lorenzo, Hennig, Philipp

Volltext bestellen

Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective von Lin, Wu, Dangel, Felix, Eschenhagen, Runa, Bae, Juhan, Turner, Richard E, Makhzani, Alireza

Volltext bestellen

Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC von Lin, Wu, Dangel, Felix, Eschenhagen, Runa, Neklyudov, Kirill, Kristiadi, Agustinus, Turner, Richard E, Makhzani, Alireza

Volltext bestellen

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures von Eschenhagen, Runa, Immer, Alexander, Turner, Richard E, Schneider, Frank, Hennig, Philipp

Volltext bestellen

Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning von Eschenhagen, Runa, Daxberger, Erik, Hennig, Philipp, Kristiadi, Agustinus

Volltext bestellen

Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks von Kristiadi, Agustinus, Eschenhagen, Runa, Hennig, Philipp

Volltext

Laplace Redux -- Effortless Bayesian Deep Learning von Daxberger, Erik, Kristiadi, Agustinus, Immer, Alexander, Eschenhagen, Runa, Bauer, Matthias, Hennig, Philipp

Volltext bestellen

Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization von Kristiadi, Agustinus, Immer, Alexander, Eschenhagen, Runa, tuin, Vincent

Volltext

Influence Functions for Scalable Data Attribution in Diffusion Models von Mlodozeniec, Bruno, Eschenhagen, Runa, Bae, Juhan, Immer, Alexander, Krueger, David, Turner, Richard

Volltext

Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective von Wu, Lin, Dangel, Felix, Eschenhagen, Runa, Bae, Juhan, Turner, Richard E, Makhzani, Alireza

Volltext

Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC von Wu, Lin, Dangel, Felix, Eschenhagen, Runa, Neklyudov, Kirill, Kristiadi, Agustinus, Turner, Richard E, Makhzani, Alireza

Volltext

Continual Deep Learning by Functional Regularisation of Memorable Past von Pan, Pingbo, Swaroop, Siddharth, Immer, Alexander, Eschenhagen, Runa, Turner, Richard E, Khan, Mohammad Emtiyaz

Volltext bestellen

Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs von Magnani, Emilia, Krämer, Nicholas, Eschenhagen, Runa, Rosasco, Lorenzo, Hennig, Philipp

Volltext

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures von Eschenhagen, Runa, Immer, Alexander, Turner, Richard E, Schneider, Frank, Hennig, Philipp

Volltext

Benchmarking Neural Network Training Algorithms von Dahl, George E, Schneider, Frank, Nado, Zachary, Agarwal, Naman, Sastry, Chandramouli Shama, Hennig, Philipp, Medapati, Sourabh, Eschenhagen, Runa, Kasimbeg, Priya, Suo, Daniel, Bae, Juhan, Gilmer, Justin, Peirson, Abel L, Khan, Bilal, Anil, Rohan, Rabbat, Mike, Krishnan, Shankar, Snider, Daniel, Amid, Ehsan, Chen, Kongtao, Maddison, Chris J, Vasudev, Rakshith, Badura, Michal, Garg, Ankush, Mattson, Peter

Volltext bestellen

Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning von Eschenhagen, Runa, Daxberger, Erik, Hennig, Philipp, Kristiadi, Agustinus

Volltext

Practical Deep Learning with Bayesian Principles von Osawa, Kazuki, Swaroop, Siddharth, Jain, Anirudh, Eschenhagen, Runa, Turner, Richard E, Yokota, Rio, Khan, Mohammad Emtiyaz

Volltext bestellen