On Descent from Local Minima

نویسندگان
چکیده

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima

We consider the problem of learning a one-hidden-layer neural network with non-overlapping convolutional layer and ReLU activation function, i.e., f(Z; w,a) = ∑ j ajσ(w Zj), in which both the convolutional weights w and the output weights a are parameters to be learned. We prove that with Gaussian input Z, there is a spurious local minimum that is not a global mininum. Surprisingly, in the pres...

متن کامل

Local Minima and Attractors at In nity for Gradient Descent Learning Algorithms

In the paper Learning Nonlinearly Parametrized Decision Re gions an online scheme for learning a very general class of decision regions is given together with conditions on both the parametriza tion and on the sequence of input examples under which good learn ing can be guaranteed to occur In this paper we discuss these condi tions in particular the requirement that there be no non global local...

متن کامل

Local Minima Embedding

Dimensionality reduction is a commonly used step in many algorithms for visualization, classification, clustering and modeling. Most dimensionality reduction algorithms find a low dimensional embedding that preserves the structure of high-dimensional data points. This paper proposes Local Minima Embedding (LME), a technique to find a lowdimensional embedding that preserves the local minima stru...

متن کامل

Continuity of Minima: Local Results

This paper compares and generalizes Berge’s maximum theorem for noncompact image sets established in Feinberg, Kasyanov and Voorneveld [5] and the local maximum theorem established in Bonnans and Shapiro [3, Proposition 4.4].

متن کامل

Adiabatic optimization without local minima

Several previous works have investigated the circumstances under which quantum adiabatic optimization algorithms can tunnel out of local energy minima that trap simulated annealing or other classical local search algorithms. Here we investigate the even more basic question of whether adiabatic optimization algorithms always succeed in polynomial time for trivial optimization problems in which t...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Mathematics of Computation

سال: 1971

ISSN: 0025-5718

DOI: 10.2307/2005219