Get started
Author

Liam Hodgkinson

Observed name: Hodgkinson, Liam
ORCID: 0000-0002-4595-0347
Observed ORCID: 0000-0002-4595-0347
OpenAlex ID: A5030249020
Lipschitz Recurrent Neural Networks
2020 · Erichson, N. Benjamin, Azencot, Omri, et al. · arXiv (Cornell University) · 87
PDF
Stochastic Normalizing Flows
2020 · Hodgkinson, Liam, van der Heide, Chris, et al. · arXiv (Cornell University) · 60
PDF
Multiplicative noise and heavy tails in stochastic optimization
2020 · Hodgkinson, Liam, Mahoney, Michael W. · arXiv (Cornell University) · 49
PDF
Test Accuracy vs. Generalization Gap: Model Selection in NLP without Accessing Training or Testing Data
2023 · Yaoqing Yang, Ryan Theisen, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · 37
PDF
Noisy Recurrent Neural Networks
2021 · Lim, Soon Hoe, Erichson, N. Benjamin, et al. · arXiv (Cornell University) · 33
PDF
The reproducing Stein kernel approach for post-hoc corrected sampling
2020 · Hodgkinson, Liam, Salomone, Robert, et al. · arXiv (Cornell University) · 32
PDF
Taxonomizing local versus global structure in neural network loss landscapes
2021 · Yang, Yaoqing, Hodgkinson, Liam, et al. · arXiv (Cornell University) · 22
PDF
Shadow Manifold Hamiltonian Monte Carlo.
2021 · Christopher van der Heide, Fred Roosta, et al. · International Conference on Artificial Intelligence and Statistics · 18
The Interpolating Information Criterion for Overparameterized Models
2023 · Hodgkinson, Liam, van der Heide, Chris, et al. · arXiv (Cornell University) · 17
PDF
Uncertainty Quantification with the Empirical Neural Tangent Kernel
2025 · Joseph Wilson, Chris van der Heide, et al. · neural information processing systems · 8
PDF
When are ensembles really effective?
2023 · Ryan Theisen, Hyunsuk Kim, et al. · neural information processing systems · 8
PDF
Stateful ODE-Nets using Basis Function Expansions
2021 · Queiruga, Alejandro, Erichson, N. Benjamin, et al. · arXiv (Cornell University) · 8
PDF
Models of Heavy-Tailed Mechanistic Universality
2025 · Hodgkinson, Liam, Wang, Zhichao, et al. · arXiv (Cornell University) · 7
PDF
Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers
2021 · Hodgkinson, Liam, Şimşekli, Umut, et al. · arXiv (Cornell University) · 7
PDF
Normal approximations for discrete-time occupancy processes
2020 · Liam Hodgkinson, Ross McVinish, et al. · Stochastic Processes and their Applications · 6
Implicit Langevin Algorithms for Sampling From Log-concave Densities
2019 · Hodgkinson, Liam, Salomone, Robert, et al. · arXiv (Cornell University) · 5
PDF
Computationally assisted proof of a novel O(3)×O(10)‐invariant Einstein metric on S12
2026 · Timothy Buttsworth, Liam Hodgkinson · Journal of the London Mathematical Society · 4
PDF
Determinant Estimation under Memory Constraints and Neural Scaling Laws
2025 · Ameli, Siavash, van der Heide, Chris, et al. · arXiv (Cornell University) · 3
PDF
Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes
2022 · Hodgkinson, Liam, van der Heide, Chris, et al. · arXiv (Cornell University) · 3
PDF
Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flows
2022 · Liang, Feynman, Hodgkinson, Liam, et al. · arXiv (Cornell University) · 3
PDF
Generalization Properties of Stochastic Optimizers via Trajectory Analysis.
2021 · Liam Hodgkinson, Umut Şimşekli, et al. · arXiv (Cornell University) · 3
Stochastic Continuous Normalizing Flows: Training SDEs as ODEs
2021 · Liam Hodgkinson, Chris van der Heide, et al. · Uncertainty in Artificial Intelligence · 3
Is the Last Layer Sufficient for Uncertainty Quantification?
2026 · Wilson, Joseph, van der Heide, Chris, et al. · arXiv (Cornell University) · 1
PDF
Spectral Estimation with Free Decompression
2025 · Siavash Ameli, Chris van der Heide, et al. · neural information processing systems · 1
PDF
Preserving Angles Improves Feature Distillation
2024 · Mannix, Evelyn J., Hodgkinson, Liam, et al. · arXiv (Cornell University) · 1
PDF
Works count: 45
Citation count: 435
H-index: 9
I10-index: 9
Year
Topic
Type