Runa Eschenhagen

30 papers A* 9Journal 21

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory. CoRR Runa Eschenhagen, Anna Cai, Tsung-Hsien Lee, Hao-Jun Michael Shi
2025	J	`jnl`	Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition. CoRR Priya Kasimbeg, Frank Schneider, Runa Eschenhagen, Juhan Bae, Chandramouli Shama Sastry, Mark Saroufim, Boyuan Feng, Less Wright, Edward Z. Yang, Zachary Nado, Sourabh Medapati, Philipp Hennig, Michael Rabbat, George E. Dahl
2025	A*	`conf`	Accelerating neural network training: An analysis of the AlgoPerf competition. ICLR Priya Kasimbeg, Frank Schneider, Runa Eschenhagen, Juhan Bae, Chandramouli Shama Sastry, Mark Saroufim, Boyuan Feng, Less Wright, Edward Z. Yang, Zachary Nado, Sourabh Medapati, Philipp Hennig, Michael Rabbat, George E. Dahl
2025	J	`jnl`	Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs. Trans. Mach. Learn. Res. Emilia Magnani, Nicholas Krämer, Runa Eschenhagen, Lorenzo Rosasco, Philipp Hennig
2025	J	`jnl`	Better Hessians Matter: Studying the Impact of Curvature Approximations in Influence Functions. CoRR Steve Hong, Runa Eschenhagen, Bruno Mlodozeniec, Richard E. Turner
2025	A*	`conf`	Influence Functions for Scalable Data Attribution in Diffusion Models. ICLR Bruno Kacper Mlodozeniec, Runa Eschenhagen, Juhan Bae, Alexander Immer, David Krueger, Richard E. Turner
2025	J	`jnl`	Kronecker-factored Approximate Curvature (KFAC) From Scratch. CoRR Felix Dangel, Bálint Mucsányi, Tobias Weber, Runa Eschenhagen
2025	J	`jnl`	Position: Curvature Matrices Should Be Democratized via Linear Operators. CoRR Felix Dangel, Runa Eschenhagen, Weronika Ormaniec, Andres Fernandez, Lukas Tatzel, Agustinus Kristiadi
2025	J	`jnl`	Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner. CoRR Runa Eschenhagen, Aaron Defazio, Tsung-Hsien Lee, Richard E. Turner, Hao-Jun Michael Shi
2025	J	`jnl`	Spectral-factorized Positive-definite Curvature Learning for NN Training. CoRR Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae, Richard E. Turner, Roger B. Grosse
2025	J	`jnl`	Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization. CoRR Wu Lin, Scott C. Lowe, Felix Dangel, Runa Eschenhagen, Zikun Xu, Roger B. Grosse
2024	A*	`conf`	Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective. ICML Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae, Richard E. Turner, Alireza Makhzani
2024	J	`jnl`	Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective. CoRR Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae, Richard E. Turner, Alireza Makhzani
2024	J	`jnl`	Influence Functions for Scalable Data Attribution in Diffusion Models. CoRR Bruno Mlodozeniec, Runa Eschenhagen, Juhan Bae, Alexander Immer, David Krueger, Richard E. Turner
2024	A*	`conf`	Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC. ICML Wu Lin, Felix Dangel, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard E. Turner, Alireza Makhzani
2023	J	`jnl`	Benchmarking Neural Network Training Algorithms. CoRR George E. Dahl, Frank Schneider, Zachary Nado, Naman Agarwal, Chandramouli Shama Sastry, Philipp Hennig, Sourabh Medapati, Runa Eschenhagen, Priya Kasimbeg, Daniel Suo, Juhan Bae, Justin Gilmer, Abel L. Peirson, Bilal Khan, Rohan Anil, Mike Rabbat, Shankar Krishnan, Daniel Snider, Ehsan Amid, Kongtao Chen, Chris J. Maddison, Rakshith Vasudev, Michal Badura, Ankush Garg, Peter Mattson
2023	A*	`conf`	Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures. NeurIPS Runa Eschenhagen, Alexander Immer, Richard E. Turner, Frank Schneider, Philipp Hennig
2023	J	`jnl`	Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures. CoRR Runa Eschenhagen, Alexander Immer, Richard E. Turner, Frank Schneider, Philipp Hennig
2023	J	`jnl`	Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization. CoRR Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Vincent Fortuin
2023	J	`jnl`	Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets. CoRR Wu Lin, Felix Dangel, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard E. Turner, Alireza Makhzani
2022	J	`jnl`	Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs. CoRR Emilia Magnani, Nicholas Krämer, Runa Eschenhagen, Lorenzo Rosasco, Philipp Hennig
2022	A*	`conf`	Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks. NeurIPS Agustinus Kristiadi, Runa Eschenhagen, Philipp Hennig
2022	J	`jnl`	Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks. CoRR Agustinus Kristiadi, Runa Eschenhagen, Philipp Hennig
2021	A*	`conf`	Laplace Redux - Effortless Bayesian Deep Learning. NeurIPS Erik A. Daxberger, Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Matthias Bauer, Philipp Hennig
2021	J	`jnl`	Laplace Redux - Effortless Bayesian Deep Learning. CoRR Erik A. Daxberger, Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Matthias Bauer, Philipp Hennig
2021	J	`jnl`	Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning. CoRR Runa Eschenhagen, Erik A. Daxberger, Philipp Hennig, Agustinus Kristiadi
2020	A*	`conf`	Continual Deep Learning by Functional Regularisation of Memorable Past. NeurIPS Pingbo Pan, Siddharth Swaroop, Alexander Immer, Runa Eschenhagen, Richard E. Turner, Mohammad Emtiyaz Khan
2020	J	`jnl`	Continual Deep Learning by Functional Regularisation of Memorable Past. CoRR Pingbo Pan, Siddharth Swaroop, Alexander Immer, Runa Eschenhagen, Richard E. Turner, Mohammad Emtiyaz Khan
2019	A*	`conf`	Practical Deep Learning with Bayesian Principles. NeurIPS Kazuki Osawa, Siddharth Swaroop, Mohammad Emtiyaz Khan, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota
2019	J	`jnl`	Practical Deep Learning with Bayesian Principles. CoRR Kazuki Osawa, Siddharth Swaroop, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota, Mohammad Emtiyaz Khan