Follow
Liam Hodgkinson
Liam Hodgkinson
Verified email at unimelb.edu.au - Homepage
Title
Cited by
Cited by
Year
Lipschitz recurrent neural networks
NB Erichson, O Azencot, A Queiruga, L Hodgkinson, MW Mahoney
arXiv preprint arXiv:2006.12070, 2020
602020
Multiplicative noise and heavy tails in stochastic optimization
L Hodgkinson, M Mahoney
International Conference on Machine Learning, 4262-4274, 2021
412021
The reproducing Stein kernel approach for post-hoc corrected sampling
L Hodgkinson, R Salomone, F Roosta
arXiv preprint arXiv:2001.09266, 2020
242020
Noisy recurrent neural networks
SH Lim, NB Erichson, L Hodgkinson, MW Mahoney
Advances in Neural Information Processing Systems 34, 5124-5137, 2021
232021
Stochastic normalizing flows
L Hodgkinson, C van der Heide, F Roosta, MW Mahoney
arXiv preprint arXiv:2002.09547, 2020
202020
Shadow manifold hamiltonian monte carlo
C van der Heide, F Roosta, L Hodgkinson, D Kroese
International Conference on Artificial Intelligence and Statistics, 1477-1485, 2021
92021
Implicit Langevin algorithms for sampling from log-concave densities
L Hodgkinson, R Salomone, F Roosta
The Journal of Machine Learning Research 22 (1), 6055-6084, 2021
82021
Stateful ode-nets using basis function expansions
A Queiruga, NB Erichson, L Hodgkinson, MW Mahoney
Advances in Neural Information Processing Systems 34, 21770-21781, 2021
72021
Taxonomizing local versus global structure in neural network loss landscapes
Y Yang, L Hodgkinson, R Theisen, J Zou, JE Gonzalez, K Ramchandran, ...
Advances in Neural Information Processing Systems 34, 18722-18733, 2021
72021
Generalization properties of stochastic optimizers via trajectory analysis
L Hodgkinson, U ¬im║ekli, R Khanna, MW Mahoney
arXiv preprint arXiv:2108.00781, 2021
62021
Normal approximations for discrete-time occupancy processes
L Hodgkinson, R McVinish, PK Pollett
Stochastic Processes and their Applications 130 (10), 6414-6444, 2020
62020
Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers
L Hodgkinson, U Simsekli, R Khanna, M Mahoney
International Conference on Machine Learning, 8774-8795, 2022
42022
Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data
Y Yang, R Theisen, L Hodgkinson, JE Gonzalez, K Ramchandran, ...
arXiv preprint arXiv:2202.02842, 2022
42022
Fast approximate simulation of finite long-range spin systems
R McVinish, L Hodgkinson
The Annals of Applied Probability 31 (3), 1443-1473, 2021
32021
Stochastic continuous normalizing flows: training SDEs as ODEs
L Hodgkinson, C van der Heide, F Roosta, MW Mahoney
Uncertainty in Artificial Intelligence, 1130-1140, 2021
22021
Compressing Deep ODE-Nets using Basis Function Expansions.
A Queiruga, NB Erichson, L Hodgkinson, MW Mahoney
arXiv preprint arXiv:2106.10820, 2021
12021
Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes
L Hodgkinson, C van der Heide, F Roosta, MW Mahoney
arXiv preprint arXiv:2210.07612, 2022
2022
Fat–Tailed Variational Inference with Anisotropic Tail Adaptive Flows
F Liang, M Mahoney, L Hodgkinson
International Conference on Machine Learning, 13257-13270, 2022
2022
Geometric rates of convergence for kernel-based sampling algorithms
R Khanna, L Hodgkinson, MW Mahoney
Uncertainty in Artificial Intelligence, 2156-2164, 2021
2021
Approximations for finite spin systems and occupancy processes
L Hodgkinson
2019
The system can't perform the operation now. Try again later.
Articles 1–20