Hodgkinson, Liam

24 publications

TMLR 2025 ComFe: An Interpretable Head for Vision Transformers Evelyn Mannix, Liam Hodgkinson, Howard Bondell

ICML 2025 Determinant Estimation Under Memory Constraints and Neural Scaling Laws Siavash Ameli, Chris Van Der Heide, Liam Hodgkinson, Fred Roosta, Michael W. Mahoney

ICML 2025 Models of Heavy-Tailed Mechanistic Universality Liam Hodgkinson, Zhichao Wang, Michael W. Mahoney

TMLR 2025 Preserving Angles Improves Feature Distillation Evelyn Mannix, Liam Hodgkinson, Howard Bondell

NeurIPS 2025 Spectral Estimation with Free Decompression Siavash Ameli, Chris van der Heide, Liam Hodgkinson, Michael W. Mahoney

UAI 2025 Temperature Optimization for Bayesian Deep Learning Kenyon Ng, Chris Heide, Liam Hodgkinson, Susan Wei

NeurIPS 2025 Uncertainty Quantification with the Empirical Neural Tangent Kernel Joseph Wilson, Chris van der Heide, Liam Hodgkinson, Fred Roosta

NeurIPS 2024 How Many Classifiers Do We Need? Hyunsuk Kim, Liam Hodgkinson, Ryan Theisen, Michael W. Mahoney

NeurIPS 2023 A Heavy-Tailed Algebra for Probabilistic Programming Feynman T Liang, Liam Hodgkinson, Michael W. Mahoney

NeurIPSW 2023 A PAC-Bayesian Perspective on the Interpolating Information Criterion Liam Hodgkinson, Chris van der Heide, Robert Salomone, Fred Roosta, Michael Mahoney

COLT 2023 Generalization Guarantees via Algorithm-Dependent Rademacher Complexity Sarah Sachs, Tim Erven, Liam Hodgkinson, Rajiv Khanna, Umut Şimşekli

ICML 2023 Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes Liam Hodgkinson, Chris Van Der Heide, Fred Roosta, Michael W. Mahoney

NeurIPS 2023 When Are Ensembles Really Effective? Ryan Theisen, Hyunsuk Kim, Yaoqing Yang, Liam Hodgkinson, Michael W. Mahoney

ICML 2022 Fat–Tailed Variational Inference with Anisotropic Tail Adaptive Flows Feynman Liang, Michael Mahoney, Liam Hodgkinson

ICML 2022 Generalization Bounds Using Lower Tail Exponents in Stochastic Optimizers Liam Hodgkinson, Umut Simsekli, Rajiv Khanna, Michael Mahoney

AISTATS 2021 Shadow Manifold Hamiltonian Monte Carlo Chris Heide, Fred Roosta, Liam Hodgkinson, Dirk Kroese

UAI 2021 Geometric Rates of Convergence for Kernel-Based Sampling Algorithms Rajiv Khanna, Liam Hodgkinson, Michael W. Mahoney

JMLR 2021 Implicit Langevin Algorithms for Sampling from Log-Concave Densities Liam Hodgkinson, Robert Salomone, Fred Roosta

ICLR 2021 Lipschitz Recurrent Neural Networks N. Benjamin Erichson, Omri Azencot, Alejandro Queiruga, Liam Hodgkinson, Michael W. Mahoney

ICML 2021 Multiplicative Noise and Heavy Tails in Stochastic Optimization Liam Hodgkinson, Michael Mahoney

NeurIPS 2021 Noisy Recurrent Neural Networks Soon Hoe Lim, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney

NeurIPS 2021 Stateful ODE-Nets Using Basis Function Expansions Alejandro Queiruga, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney

UAI 2021 Stochastic Continuous Normalizing Flows: Training SDEs as ODEs Liam Hodgkinson, Chris Heide, Fred Roosta, Michael W. Mahoney

NeurIPS 2021 Taxonomizing Local Versus Global Structure in Neural Network Loss Landscapes Yaoqing Yang, Liam Hodgkinson, Ryan Theisen, Joe Zou, Joseph E Gonzalez, Kannan Ramchandran, Michael W. Mahoney