Results 21 to 30 of about 32,351,759 (213)

Domain‐adapted driving scene understanding with uncertainty‐aware and diversified generative adversarial networks

open access: yesCAAI Transactions on Intelligence Technology, EarlyView., 2023
Abstract Autonomous vehicles are required to operate in an uncertain environment. Recent advances in computational intelligence techniques make it possible to understand driving scenes in various environments by using a semantic segmentation neural network, which assigns a class label to each pixel.
Yining Hua   +4 more
wiley   +1 more source

TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization [PDF]

open access: yesInternational Conference on Learning Representations, 2022
Adaptive gradient methods have shown their ability to adjust the stepsizes on the fly in a parameter-agnostic manner, and empirically achieve faster convergence for solving minimization problems.
Xiang Li, Junchi Yang, Niao He
semanticscholar   +1 more source

Sion's Minimax Theorem in Geodesic Metric Spaces and a Riemannian Extragradient Algorithm [PDF]

open access: yesSIAM Journal on Optimization, 2022
Deciding whether saddle points exist or are approximable for nonconvex-nonconcave problems is usually intractable. This paper takes a step towards understanding a broad class of nonconvex-nonconcave minimax problems that do remain tractable. Specifically,
Peiyuan Zhang, J. Zhang, S. Sra
semanticscholar   +1 more source

Semi-Supervised Domain Adaptation via Minimax Entropy [PDF]

open access: yesIEEE International Conference on Computer Vision, 2019
Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision. However, we show that these techniques perform poorly when even a few labeled examples are available ...
Kuniaki Saito   +4 more
semanticscholar   +1 more source

Infinitely Many Periodic Solutions for Nonautonomous Sublinear Second-Order Hamiltonian Systems

open access: yesAbstract and Applied Analysis, 2010
Two sequences of distinct periodic solutions for second-order Hamiltonian systems with sublinear nonlinearity are obtained by using the minimax methods.
Peng Zhang, Chun-Lei Tang
doaj   +1 more source

Periodic Solutions for Subquadratic Discrete Hamiltonian Systems

open access: yesAdvances in Difference Equations, 2007
Some existence conditions of periodic solutions are obtained for a class of nonautono mous subquadratic first-order discrete Hamiltonian systems by the minimax methods in the critical point theory.
Xiaoqing Deng
doaj   +2 more sources

On periodic solutions of nonautonomous second order Hamiltonian systems with $(q,p)$-Laplacian

open access: yesElectronic Journal of Qualitative Theory of Differential Equations, 2016
A new existence result is obtained for nonautonomous second order Hamiltonian systems with $(q,p)$-Laplacian by using the minimax methods.
Daniel Pasca, Zhiyong Wang
doaj   +1 more source

Minimax rates for heterogeneous causal effect estimation. [PDF]

open access: yesAnn Stat, 2022
Estimation of heterogeneous causal effects - i.e., how effects of policies and treatments vary across subjects - is a fundamental task in causal inference.
Kennedy EH   +3 more
europepmc   +3 more sources

DNase1 RS1053874 Polymorphism is Associated with Early Neurological Recovery through NET Modulation and with Long‐Term Survival in Ischemic Stroke: A Prospective Cohort Study

open access: yesAnnals of Neurology, EarlyView.
Objective Immunothrombosis contributes to ischemic stroke pathophysiology through neutrophil extracellular trap (NET) formation, which promotes thrombus stabilization and microvascular dysfunction. DNase1 is the principal endonuclease responsible for NET degradation.
B. Díaz‐Benito   +10 more
wiley   +1 more source

Hidden Markov graphical models with state‐dependent generalized hyperbolic distributions

open access: yesCanadian Journal of Statistics, EarlyView.
Abstract In this article, we develop a novel hidden Markov graphical model to investigate time‐varying interconnectedness between different financial markets. To identify conditional correlation structures under varying market conditions and accommodate shape features embedded in financial time series, we rely upon the generalized hyperbolic family of ...
Beatrice Foroni   +2 more
wiley   +1 more source

Home - About - Disclaimer - Privacy