Lin, Wu

14 publications

ICLR 2026 Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization Wu Lin, Scott C. Lowe, Felix Dangel, Runa Eschenhagen, Zikun Xu, Roger Baker Grosse

ICML 2024 Can We Remove the Square-Root in Adaptive Gradient Methods? a Second-Order Perspective Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae, Richard E. Turner, Alireza Makhzani

ICML 2024 Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC Wu Lin, Felix Dangel, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard E. Turner, Alireza Makhzani

NeurIPS 2024 Training Data Attribution via Approximate Unrolling Juhan Bae, Wu Lin, Jonathan Lorraine, Roger Grosse

ICML 2023 Simplifying Momentum-Based Positive-Definite Submanifold Optimization with Applications to Deep Learning Wu Lin, Valentin Duruisseaux, Melvin Leok, Frank Nielsen, Mohammad Emtiyaz Khan, Mark Schmidt

NeurIPSW 2023 Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets Wu Lin, Felix Dangel, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard E. Turner, Alireza Makhzani

NeurIPSW 2022 Practical Structured Riemannian Optimization with Momentum by Using Generalized Normal Coordinates Wu Lin, Valentin Duruisseaux, Melvin Leok, Frank Nielsen, Mohammad Emtiyaz Khan, Mark Schmidt

ICML 2021 Tractable Structured Natural-Gradient Descent Using Local Parameterizations Wu Lin, Frank Nielsen, Khan Mohammad Emtiyaz, Mark Schmidt

ICML 2020 Handling the Positive-Definite Constraint in the Bayesian Learning Rule Wu Lin, Mark Schmidt, Mohammad Emtiyaz Khan

ICML 2019 Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-Family Approximations Wu Lin, Mohammad Emtiyaz Khan, Mark Schmidt

ICML 2018 Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam Mohammad Khan, Didrik Nielsen, Voot Tangkaratt, Wu Lin, Yarin Gal, Akash Srivastava

ICLR 2018 Variational Message Passing with Structured Inference Networks Wu Lin, Nicolas Hubacher, Mohammad Emtiyaz Khan

AISTATS 2017 Conjugate-Computation Variational Inference: Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models Mohammad Emtiyaz Khan, Wu Lin

UAI 2016 Faster Stochastic Variational Inference Using Proximal-Gradient Methods with General Divergence Functions Mohammad Emtiyaz Khan, Reza Babanezhad, Wu Lin, Mark Schmidt, Masashi Sugiyama