10 citations · 20 across the 4 of their papers we have counts for
4 papers
U-Clip: On-Average Unbiased Stochastic Gradient Clipping
Bryn Elesedy, Marcus Hutter
U-Clip is a simple amendment to gradient clipping that can be applied to any iterative gradient optimization algorithm. Like regular clipping, U-Clip involves using gradients that…
Provably Strict Generalisation Benefit for Invariance in Kernel Methods
Bryn Elesedy
It is a commonly held belief that enforcing invariance improves generalisation. Although this approach enjoys widespread popularity, it is only very recently that a rigorous theore…
Provably Strict Generalisation Benefit for Equivariant Models
Bryn Elesedy, Sheheryar Zaidi
It is widely believed that engineering a model to be invariant/equivariant improves generalisation. Despite the growing popularity of this approach, a precise characterisation of t…
Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning
Bryn Elesedy, Varun Kanade, Yee Whye Teh
We analyse the pruning procedure behind the lottery ticket hypothesis arXiv:1803.03635v5, iterative magnitude pruning (IMP), when applied to linear models trained by gradient flow.…