no code implementations • 4 Oct 2022 • Daniel D. Johnson, Ayoub El Hanchi, Chris J. Maddison
We give generalization bounds for downstream linear prediction using our Kernel PCA representation, and show empirically on a set of synthetic tasks that applying Kernel PCA to contrastive learning models can indeed approximately recover the Markov chain eigenfunctions, although the accuracy depends on the kernel parameterization as well as on the augmentation strength.
no code implementations • 23 Mar 2021 • Ayoub El Hanchi, David A. Stephens
Despite the strong theoretical guarantees that variance-reduced finite-sum optimization algorithms enjoy, their applicability remains limited to cases where the memory overhead they introduce (SAG/SAGA), or the periodic full gradient computation they require (SVRG/SARAH) are manageable.
no code implementations • NeurIPS 2020 • Ayoub El Hanchi, David A. Stephens
Reducing the variance of the gradient estimator is known to improve the convergence rate of stochastic gradient-based optimization and sampling algorithms.