Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Moniri, Behrad"'
Autor:
Moniri, Behrad, Hassani, Hamed
In this paper we study the asymptotics of linear regression in settings with non-Gaussian covariates where the covariates exhibit a linear dependency structure, departing from the standard assumption of independence. We model the covariates using sto
Externí odkaz:
http://arxiv.org/abs/2412.03702
Large Language Models (LLMs) are rapidly evolving and impacting various fields, necessitating the development of effective methods to evaluate and compare their performance. Most current approaches for performance evaluation are either based on fixed
Externí odkaz:
http://arxiv.org/abs/2406.11044
Autor:
Moniri, Behrad, Hassani, Hamed
In this paper, we study a nonlinear spiked random matrix model where a nonlinear function is applied element-wise to a noise matrix perturbed by a rank-one signal. We establish a signal-plus-noise decomposition for this model and identify precise pha
Externí odkaz:
http://arxiv.org/abs/2405.18274
Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks under certain conditions, one step of gradient descent on the first lay
Externí odkaz:
http://arxiv.org/abs/2310.07891
Evaluating the performance of machine learning models under distribution shift is challenging, especially when we only have unlabeled data from the shifted (target) domain, along with labeled data from the original (source) domain. Recent work sugges
Externí odkaz:
http://arxiv.org/abs/2301.13371
Two main concepts studied in machine learning theory are generalization gap (difference between train and test error) and excess risk (difference between test error and the minimum possible error). While information-theoretic tools have been used ext
Externí odkaz:
http://arxiv.org/abs/2202.07537
In parametric Bayesian learning, a prior is assumed on the parameter $W$ which determines the distribution of samples. In this setting, Minimum Excess Risk (MER) is defined as the difference between the minimum expected loss achievable when learning
Externí odkaz:
http://arxiv.org/abs/2105.04180
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.