Zobrazeno 1 - 10
of 100
pro vyhledávání: '"Erdogdu, Murat A."'
Given a collection of feature maps indexed by a set $\mathcal{T}$, we study the performance of empirical risk minimization (ERM) on regression problems with square loss over the union of the linear classes induced by these feature maps. This setup ai
Externí odkaz:
http://arxiv.org/abs/2411.12029
Recently, there have been numerous studies on feature learning with neural networks, specifically on learning single- and multi-index models where the target is a function of a low-dimensional projection of the input. Prior works have shown that in h
Externí odkaz:
http://arxiv.org/abs/2410.16449
We study the problem of learning multi-index models in high-dimensions using a two-layer neural network trained with the mean-field Langevin algorithm. Under mild distributional assumptions on the data, we characterize the effective dimension $d_{\ma
Externí odkaz:
http://arxiv.org/abs/2408.07254
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:
Vural, Nuri Mert, Erdogdu, Murat A.
While it is commonly observed in practice that pruning networks to a certain level of sparsity can improve the quality of the features, a theoretical explanation of this phenomenon remains elusive. In this work, we investigate this by demonstrating t
Externí odkaz:
http://arxiv.org/abs/2406.08658
We study the complexity of heavy-tailed sampling and present a separation result in terms of obtaining high-accuracy versus low-accuracy guarantees i.e., samplers that require only $O(\log(1/\varepsilon))$ versus $\Omega(\text{poly}(1/\varepsilon))$
Externí odkaz:
http://arxiv.org/abs/2405.16736
We study the complexity of sampling from the stationary distribution of a mean-field SDE, or equivalently, the complexity of minimizing a functional over the space of probability measures which includes an interaction term. Our main insight is to dec
Externí odkaz:
http://arxiv.org/abs/2402.07355
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
Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. Machine Learning (ML) models are expensive to train, in part because data is hard to obtain,
Externí odkaz:
http://arxiv.org/abs/2310.01959
Recent works have demonstrated that the sample complexity of gradient-based learning of single index models, i.e. functions that depend on a 1-dimensional projection of the input data, is governed by their information exponent. However, these results
Externí odkaz:
http://arxiv.org/abs/2309.03843