Results 111 to 120 of about 28,952 (292)
Interpolation, growth conditions, and stochastic gradient descent
, 2020 Current machine learning practice requires solving huge-scale empirical risk minimization problems quickly and robustly. These problems are often highly under-determined and admit multiple solutions which exactly fit, or interpolate, the training data ...
Mishkin, Aaron
core
Advanced Materials Technologies, EarlyView.ABSTRACT Real‐time insight into local chemistry is critical for reliable part quality in additive manufacturing, especially laser powder bed fusion (PBF‑LB/M), where rapid thermal cycles and localized evaporation can undermine part performance. Optical emission spectroscopy (OES) offers non‑intrusive, in situ plume monitoring, but detection geometry ...
Philipp Gabriel +4 more
wiley +1 more source
Unforgeability in Stochastic Gradient Descent
Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023 Teodora Baluta +4 more
openaire +1 more source
Recent Advances of Slip Sensors for Smart Robotics
Advanced Materials Technologies, EarlyView.This review summarizes recent progress in robotic slip sensors across mechanical, electrical, thermal, optical, magnetic, and acoustic mechanisms, offering a comprehensive reference for the selection of slip sensors in robotic applications. In addition, current challenges and emerging trends are identified to advance the development of robust, adaptive,
Xingyu Zhang +8 more
wiley +1 more source
Mixing of Stochastic Accelerated Gradient Descent
CoRR, 2019 We study the mixing properties for stochastic accelerated gradient descent (SAGD) on least-squares regression. First, we show that stochastic gradient descent (SGD) and SAGD are simulating the same invariant distribution. Motivated by this, we then establish mixing rate for SAGD-iterates and compare it with those of SGD-iterates.
Peiyuan Zhang +2 more
openaire +2 more sources
Asymptotic Analysis of Conditioned Stochastic Gradient Descent
, 2023 In this paper, we investigate a general class of stochastic gradient descent (SGD) algorithms, called Conditioned SGD, based on a preconditioning of the gradient direction.
Leluc, Rémi, Portier, François
core +1 more source
Advanced Materials Technologies, EarlyView.Liquid metal additives are processed in elastomer host resulting in highly conductive and stretchable composites. The material functions as a piezoresistive sensor with minimal drift, low stiffness, and enhanced operating range. The film can replace wires to charge a mobile phone at ∼350% strain and monitors bodily motion in real‐time via a portable ...
Patryk Wojciak +3 more
wiley +1 more source
Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent
, 2023 We propose new limiting dynamics for stochastic gradient descent in the small learning rate regime called stochastic modified flows. These SDEs are driven by a cylindrical Brownian motion and improve the so-called stochastic modified equations by having ...
Kassing, Sebastian +2 more
core +1 more source
Advanced Optical Materials, EarlyView.ABSTRACT Photonic integrated circuits (PICs) can deliver unparalleled performance for future neuromorphic computing applications. Such neuromorphic PICs require a large number of tunable switches, which are typically realized with current‐controlled heaters, resulting in considerable energy consumption.
Jens Samland +10 more
wiley +1 more source
Parallelized stochastic gradient descent
, 2010 With the increase in available data parallel machine learning has become an increasingly pressing problem. In this paper we present the first parallel stochastic gradient descent algorithm including a detailed analysis and experimental evidence.
Martin A Zinkevich +3 more
core