Liam Hodgkinson
19 papers · 2021–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Conference Polyglot (7) π£ Hot Topic Early Bird π§ Keyword Pioneer π Interdisciplinary Bridge π Cross-Pollinator (13)
π§
Keyword Pioneer
π€
Dynamic Duo
(12)
π
Triple Crown
π
Keyword Champion
(2)
π
Century Club
(19)
β‘
Prolific Year
(9)
β
The Questioner
(2)
ποΈ
Keyword Collector
(84)
π₯
Unstoppable
(5)
Conferences
ICML (6)
NIPS (6)
UAI (3)
AISTATS (1)
COLT (1)
ICLR (1)
JMLR (1)
Top co-authors
Keywords
neural network
(3)
stochastic differential equation
(3)
stochastic optimization
(2)
error rate
(2)
double descent
(2)
neural network optimization
(2)
heavy-tailed distribution
(2)
markov chain monte carlo
(2)
variational inference
(2)
ensemble learning
(2)
non-convex optimization
(2)
generalization bound
(2)
majority vote
(2)
batch normalization
(1)
stochastic gradient descent
(1)
uncertainty quantification
(1)
density estimation
(1)
langevin dynamics
(1)
gaussian process
(1)
image classification
(1)
Papers
Models of Heavy-Tailed Mechanistic Universality
ICML 2025
Temperature Optimization for Bayesian Deep Learning
UAI 2025
Determinant Estimation under Memory Constraints and Neural Scaling Laws
ICML 2025
How many classifiers do we need?
NIPS 2024
When are ensembles really effective?
NIPS 2023
Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes
ICML 2023
Generalization Guarantees via Algorithm-dependent Rademacher Complexity
COLT 2023
A Heavy-Tailed Algebra for Probabilistic Programming
NIPS 2023
Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers
ICML 2022
FatβTailed Variational Inference with Anisotropic Tail Adaptive Flows
ICML 2022
Multiplicative Noise and Heavy Tails in Stochastic Optimization
ICML 2021
Taxonomizing local versus global structure in neural network loss landscapes
NIPS 2021
Stateful ODE-Nets using Basis Function Expansions
NIPS 2021
Shadow Manifold Hamiltonian Monte Carlo
AISTATS 2021
Lipschitz Recurrent Neural Networks
ICLR 2021
Noisy Recurrent Neural Networks
NIPS 2021
Implicit Langevin Algorithms for Sampling From Log-concave Densities
JMLR 2021
Stochastic continuous normalizing flows: training SDEs as ODEs
UAI 2021
Geometric rates of convergence for kernel-based sampling algorithms
UAI 2021