Results 91 to 100 of about 28,952 (292)
All‐Optical Reconfigurable Physical Unclonable Function for Sustainable Security
An all‐optical reconfigurable physical unclonable function (PUF) is demonstrated using plasmonic coupling–induced sintering of optically trapped gold nanoparticles, where Brownian motion serves as a robust entropy source. The resulting optical PUF exhibits high encoding density, strong resistance to modeling attacks, and practical authentication ...
Jang‐Kyun Kwak +4 more
wiley +1 more source
Semi-Cyclic Stochastic Gradient Descent
We consider convex SGD updates with a block-cyclic structure, i.e. where each cycle consists of a small number of blocks, each with many samples from a possibly different, block-specific, distribution. This situation arises, e.g., in Federated Learning where the mobile devices available for updates at different times during the day have different ...
Hubert Eichner +4 more
openaire +3 more sources
SSRGD: Simple stochastic recursive gradient descent for escaping saddle points
We analyze stochastic gradient algorithms for optimizing nonconvex problems. In particular, our goal is to find local minima (second-order stationary points) instead of just finding first-order stationary points which may be some bad unstable saddle ...
Li, Zhize
core
Inverse Design of Amorphous Materials With Targeted Properties
AMDEN is a diffusion model framework for the inverse design of amorphous materials with targeted properties. By incorporating Hamiltonian Monte Carlo refinement into the denoising process, the framework overcomes the challenge of generating thermally relaxed disordered structures.
Jonas A. Finkler +4 more
wiley +1 more source
Communication-efficient stochastic gradient descent, with applications to neural networks
Parallel implementations of stochastic gradient descent (SGD) have received significant research attention, thanks to its excellent scalability properties.
Vojnovic, Milan +4 more
core
An Aloe‐pinspired droplet electricity generator (A‐DEG) overcomes the limited energy collection zone of conventional DEGs by guiding impact droplets through a channeling midrib and artificial cuticle. The channeling midrib induces uni‐directional droplet spreading, while the artificial cuticle on the midrib further reinforces this behavior through its ...
Gibeom Lee +8 more
wiley +1 more source
The uncertainty in the new power system has increased, leading to limitations in traditional stability analysis methods. Therefore, considering the perspective of the three-dimensional static security region (SSR), we propose a novel approach for system ...
Jiahui Wu +3 more
doaj +1 more source
AI–Guided 4D Printing of Carnivorous Plants–Inspired Microneedles for Accelerated Wound Healing
This work presents an artificial intelligence (AI)‐guided 4D‐printed microneedle platform inspired by carnivorous plants for wound healing. A thermo‐responsive shape memory polymer enables body temperature–triggered self‐coiling for autonomous wound closure.
Hyun Lee +21 more
wiley +1 more source
On the Hyperparameters in Stochastic Gradient Descent with Momentum
34 pages, 4 figures.
openaire +3 more sources
Carathéodory sampling for stochastic gradient descent
Many problems require to optimize empirical risk functions over large data sets. Gradient descent methods that calculate the full gradient in every descent step do not scale to such datasets.
Cosentino, Francesco +2 more
core +2 more sources

