Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Schechtman, Sholom"'
Autor:
Schechtman, Sholom
It is well-known that the convergence of a family of smooth functions does not imply the convergence of its gradients. In this work, we show that if the family is definable in an o-minimal structure (for instance semialgebraic, subanalytic, or any co
Externí odkaz:
http://arxiv.org/abs/2402.08272
Autor:
Chzhen, Evgenii, Schechtman, Sholom
We consider the problem of unconstrained minimization of finite sums of functions. We propose a simple, yet, practical way to incorporate variance reduction techniques into SignSGD, guaranteeing convergence that is similar to the full sign gradient d
Externí odkaz:
http://arxiv.org/abs/2305.13187
We consider the problem of minimizing a non-convex function over a smooth manifold $\mathcal{M}$. We propose a novel algorithm, the Orthogonal Directions Constrained Gradient Method (ODCGM) which only requires computing a projection onto a vector spa
Externí odkaz:
http://arxiv.org/abs/2303.09261
In this paper, we develop a new algorithm, Annealed Skewed SGD - AskewSGD - for training deep neural networks (DNNs) with quantized weights. First, we formulate the training of quantized neural networks (QNNs) as a smoothed sequence of interval-const
Externí odkaz:
http://arxiv.org/abs/2211.03741
Autor:
Schechtman, Sholom
It was previously shown by Davis and Drusvyatskiy that every Clarke critical point of a generic, semialgebraic (and more generally definable in an o-minimal structure), weakly convex function is lying on an active manifold and is either a local minim
Externí odkaz:
http://arxiv.org/abs/2109.02455
In non-smooth stochastic optimization, we establish the non-convergence of the stochastic subgradient descent (SGD) to the critical points recently called active strict saddles by Davis and Drusvyatskiy. Such points lie on a manifold $M$ where the fu
Externí odkaz:
http://arxiv.org/abs/2108.02072
Autor:
Schechtman, Sholom
We analyze the stochastic proximal subgradient descent in the case where the objective functions are path differentiable and verify a Sard-type condition. While the accumulation set may not be reduced to unique point, we show that the time spent by t
Externí odkaz:
http://arxiv.org/abs/2103.16253
Publikováno v:
Set-Valued and Variational Analysis, Springer, 2022
This paper studies the asymptotic behavior of the constant step Stochastic Gradient Descent for the minimization of an unknown function F , defined as the expectation of a non convex, non smooth, locally Lipschitz random function. As the gradient may
Externí odkaz:
http://arxiv.org/abs/2005.08513
Autor:
Schechtman, Sholom *, Tiapkin, Daniil, Moulines, Eric *, Jordan, Michael I., Muehlebach, Michael
Publikováno v:
In IFAC PapersOnLine 2022 55(16):236-241
Publikováno v:
Mathematics of Operations Research; Aug2024, Vol. 49 Issue 3, p1761-1790, 30p