no code implementations • 22 May 2024 • Kaelan Donatella, Samuel Duffield, Maxwell Aifer, Denis Melanson, Gavin Crooks, Patrick J. Coles
Second-order training methods have better convergence properties than gradient descent but are rarely used in practice for large-scale training due to their computational overhead.
no code implementations • 8 Nov 2023 • Johnathan Chiu, Samuel Duffield, Max Hunter-Gordon, Kaelan Donatella, Max Aifer, Andi Gu
We introduce a novel approach to video modeling that leverages controlled differential equations (CDEs) to address key challenges in video tasks, notably video interpolation and mask propagation.
1 code implementation • 4 Aug 2023 • Samuel Duffield, Samuel Power, Lorenzo Rimella
We summarise popular methods used for skill rating in competitive sports, along with their inferential paradigms and introduce new approaches based on sequential Monte Carlo and discrete hidden Markov models.
no code implementations • 15 Jun 2022 • Samuel Duffield, Marcello Benedetti, Matthias Rosenkranz
Currently available quantum computers suffer from constraints including hardware noise and a limited number of qubits.
1 code implementation • 8 Dec 2020 • Samuel Duffield, Sumeetpal S. Singh
We introduce a novel method for online smoothing in state-space models that utilises a fixed-lag approximation to overcome the well known issue of path degeneracy.
Methodology Applications