Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Hanchi, Ayoub El"'
We study the problem of designing minimax procedures in linear regression under the quantile risk. We start by considering the realizable setting with independent Gaussian noise, where for any given noise level and distribution of inputs, we obtain t
Externí odkaz:
http://arxiv.org/abs/2406.12145
Autor:
Hanchi, Ayoub El, Erdogdu, Murat A.
We study the performance of empirical risk minimization on the $p$-norm linear regression problem for $p \in (1, \infty)$. We show that, in the realizable case, under no moment assumptions, and up to a distribution-dependent constant, $O(d)$ samples
Externí odkaz:
http://arxiv.org/abs/2310.12437
Contrastive learning is a powerful framework for learning self-supervised representations that generalize well to downstream supervised tasks. We show that multiple existing contrastive learning methods can be reinterpreted as learning kernel functio
Externí odkaz:
http://arxiv.org/abs/2210.01883
Autor:
Hanchi, Ayoub El, Stephens, David A.
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
Externí odkaz:
http://arxiv.org/abs/2103.12293
Autor:
Hanchi, Ayoub El, Stephens, David A.
Reducing the variance of the gradient estimator is known to improve the convergence rate of stochastic gradient-based optimization and sampling algorithms. One way of achieving variance reduction is to design importance sampling strategies. Recently,
Externí odkaz:
http://arxiv.org/abs/2103.12243