Liam Hodgkinson

According to our database, Liam Hodgkinson authored at least 22 papers between 2020 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

A PAC-Bayesian Perspective on the Interpolating Information Criterion.

Liam Hodgkinson, Christopher van der Heide, Robert Salomone, Fred Roosta, Michael W. Mahoney

CoRR, 2023

The Interpolating Information Criterion for Overparameterized Models.

Liam Hodgkinson, Christopher van der Heide, Robert Salomone, Fred Roosta, Michael W. Mahoney

CoRR, 2023

When are ensembles really effective?

Ryan Theisen, Hyunsuk Kim, Yaoqing Yang, Liam Hodgkinson, Michael W. Mahoney

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Heavy-Tailed Algebra for Probabilistic Programming.

Feynman T. Liang, Liam Hodgkinson, Michael W. Mahoney

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Test Accuracy vs. Generalization Gap: Model Selection in NLP without Accessing Training or Testing Data.

Yaoqing Yang, Ryan Theisen, Liam Hodgkinson, Joseph E. Gonzalez, Kannan Ramchandran, Charles H. Martin, Michael W. Mahoney

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes.

Liam Hodgkinson, Christopher van der Heide, Fred Roosta, Michael W. Mahoney

Proceedings of the International Conference on Machine Learning, 2023

Generalization Guarantees via Algorithm-dependent Rademacher Complexity.

Sarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna, Umut Simsekli

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data.

Yaoqing Yang, Ryan Theisen, Liam Hodgkinson, Joseph E. Gonzalez, Kannan Ramchandran, Charles H. Martin, Michael W. Mahoney

CoRR, 2022

Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flows.

Feynman T. Liang, Michael W. Mahoney, Liam Hodgkinson

Proceedings of the International Conference on Machine Learning, 2022

Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers.

Liam Hodgkinson, Umut Simsekli, Rajiv Khanna, Michael W. Mahoney

Proceedings of the International Conference on Machine Learning, 2022

2021

Implicit Langevin Algorithms for Sampling From Log-concave Densities.

Liam Hodgkinson, Robert Salomone, Fred Roosta

J. Mach. Learn. Res., 2021

Generalization Properties of Stochastic Optimizers via Trajectory Analysis.

Liam Hodgkinson, Umut Simsekli, Rajiv Khanna, Michael W. Mahoney

CoRR, 2021

Compressing Deep ODE-Nets using Basis Function Expansions.

Alejandro F. Queiruga, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney

CoRR, 2021

Geometric rates of convergence for kernel-based sampling algorithms.

Rajiv Khanna, Liam Hodgkinson, Michael W. Mahoney

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

Stochastic continuous normalizing flows: training SDEs as ODEs.

Liam Hodgkinson, Christopher van der Heide, Fred Roosta, Michael W. Mahoney

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 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

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Stateful ODE-Nets using Basis Function Expansions.

Alejandro F. Queiruga, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Noisy Recurrent Neural Networks.

Soon Hoe Lim, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Multiplicative Noise and Heavy Tails in Stochastic Optimization.

Liam Hodgkinson, Michael W. Mahoney

Proceedings of the 38th International Conference on Machine Learning, 2021

Lipschitz Recurrent Neural Networks.

N. Benjamin Erichson, Omri Azencot, Alejandro F. Queiruga, Liam Hodgkinson, Michael W. Mahoney

Proceedings of the 9th International Conference on Learning Representations, 2021

Shadow Manifold Hamiltonian Monte Carlo.

Christopher van der Heide, Fred Roosta, Liam Hodgkinson, Dirk Kroese

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Stochastic Normalizing Flows.

Liam Hodgkinson, Christopher van der Heide, Fred Roosta, Michael W. Mahoney

CoRR, 2020