Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Ma, Jianhao"'
Autor:
Ma, Jianhao, Fattahi, Salar
We study the problem of symmetric matrix completion, where the goal is to reconstruct a positive semidefinite matrix $\rm{X}^\star \in \mathbb{R}^{d\times d}$ of rank-$r$, parameterized by $\rm{U}\rm{U}^{\top}$, from only a subset of its observed ent
Externí odkaz:
http://arxiv.org/abs/2402.06756
In this paper, we study the problem of robust sparse mean estimation, where the goal is to estimate a $k$-sparse mean from a collection of partially corrupted samples drawn from a heavy-tailed distribution. Existing estimators face two critical chall
Externí odkaz:
http://arxiv.org/abs/2305.15276
Autor:
Ma, Jianhao, Fattahi, Salar
We explore the local landscape of low-rank matrix recovery, aiming to reconstruct a $d_1\times d_2$ matrix with rank $r$ from $m$ linear measurements, some potentially noisy. When the true rank is unknown, overestimation is common, yielding an over-p
Externí odkaz:
http://arxiv.org/abs/2302.10963
This work analyzes the solution trajectory of gradient-based algorithms via a novel basis function decomposition. We show that, although solution trajectories of gradient-based algorithms may vary depending on the learning task, they behave almost mo
Externí odkaz:
http://arxiv.org/abs/2210.00346
Autor:
Ma, Jianhao, Fattahi, Salar
This work characterizes the effect of depth on the optimization landscape of linear regression, showing that, despite their nonconvexity, deeper models have more desirable optimization landscape. We consider a robust and over-parameterized setting, w
Externí odkaz:
http://arxiv.org/abs/2207.07612
Autor:
Ma, Jianhao, Fattahi, Salar
In this work, we study the performance of sub-gradient method (SubGM) on a natural nonconvex and nonsmooth formulation of low-rank matrix recovery with $\ell_1$-loss, where the goal is to recover a low-rank matrix from a limited number of measurement
Externí odkaz:
http://arxiv.org/abs/2202.08788
Generalization is one of the fundamental issues in machine learning. However, traditional techniques like uniform convergence may be unable to explain generalization under overparameterization. As alternative approaches, techniques based on stability
Externí odkaz:
http://arxiv.org/abs/2106.06153
Autor:
Ma, Jianhao, Fattahi, Salar
Restricted isometry property (RIP), essentially stating that the linear measurements are approximately norm-preserving, plays a crucial role in studying low-rank matrix recovery problem. However, RIP fails in the robust setting, when a subset of the
Externí odkaz:
http://arxiv.org/abs/2102.02969
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Journal of Advanced Dielectrics; Aug2024, Vol. 14 Issue 4, p1-13, 13p
