Assessing deep learning: a work program for the humanities in the age of artificial intelligence
Following the success of deep learning (DL) in research, we are now witnessing the fast and
widespread adoption of artificial intelligence (AI) in daily life, influencing the way we act …
widespread adoption of artificial intelligence (AI) in daily life, influencing the way we act …
Linearized ADMM converges to second-order stationary points for non-convex problems
In this work, a gradient-based primal-dual method of multipliers is proposed for solving a
class of linearly constrained non-convex problems. We show that with random initialization …
class of linearly constrained non-convex problems. We show that with random initialization …
Guaranteed recovery of one-hidden-layer neural networks via cross entropy
We study model recovery for data classification, where the training labels are generated
from a one-hidden-layer neural network with sigmoid activations, also known as a single …
from a one-hidden-layer neural network with sigmoid activations, also known as a single …
PA-GD: On the convergence of perturbed alternating gradient descent to second-order stationary points for structured nonconvex optimization
Alternating gradient descent (A-GD) is a simple but popular algorithm in machine learning,
which updates two blocks of variables in an alternating manner using gradient descent …
which updates two blocks of variables in an alternating manner using gradient descent …
Local geometry of cross entropy loss in learning one-hidden-layer neural networks
We study model recovery for data classification, where the training labels are generated
from a one-hidden-layer neural network with sigmoid activations, and the goal is to recover …
from a one-hidden-layer neural network with sigmoid activations, and the goal is to recover …
Локальная кривизна и точность нейросетевой аппроксимации
ММ Краснов, ВС Смолин - XXI МЕЖДУНАРОДНАЯ НАУЧНО …, 2019 - elibrary.ru
Рассматривается задача повышения точности одномерной аппроксимации функций на
нейросети с одним скрытым слоем. В качестве примера целевой функции …
нейросети с одним скрытым слоем. В качестве примера целевой функции …