De Moor, "Non-concave fundamental diagrams and phase transitions in a stochastic traffic cellular automaton," The European Physical Journal B, vol. 42, No. 1, pp. 131-140, 2004.Maerivoet, S., De Moor, B., 2004. Non-concave fundamental diagrams and phase transitions in a stochastic ...
We consider an expected utility maximization problem where the utility function is not necessarily concave and the time horizon is uncertain. We establish a necessary and sufficient condition for the optimality for general non-concave utility function in a complete financial market. We show that the ...
A class of variable selection procedures for parametric models via nonconcave penalized likelihood is proposed by Fan and Li (2001) to simultaneously estimate parameters and select important variables. They demonstrate that this class of procedures has an oracle property when the number of parameters ...
In this paper, we propose a nonconcave penalized M-estimation of the least absolute relative errors (penalized M-LARE) method for a sparse multiplicative regression model, where the dimension of model can increase with the sample size. Under certain appropriate conditions, the consistency and asympt...
In this paper, we put non-concave penalty on the local conditional likelihood. We obtain the oracle property and asymptotic normal distribution property of the parameters in Ising model. With a union band, we obtain the sign consistence for the estimator of parameter matrix, and the convergence ...
事实上,我们先证明了在MVI条件下,使用Adam optimizer的一个变种 extra-gradient AMSGrad,可以保证GAN训练的一阶收敛性,并且给出了时间复杂度估计,这也是第一个在non-convex non-concave 的 setting下针对 Adam-type algorithm 的收敛性证明,由于Adam算法中有很多为了 practical方便而加的一些trick,对于理论证明是很大...
of the nonconcave penalized likelihood are established for situations in which the number of parameters tends to ∞ as the sample size increases. Under regularity conditions we have established an oracle property and the asymptotic normality of the penalized likelihood estimators. Furthermore, the consi...
Two simple spin models are studied to show that the microcanonical entropy can be a non-concave function of the energy, and that the microcanonical and canonical ensembles can give non-equivalent descriptions of the same system in the thermodynamic limit. The two models are simple variations of ...
From the mathematical viewpoint, the main features of the model are the following: (i) the dynamics is an increasing, unbounded and not globally concave function of the state; (ii) the state variable is subject to a static constraint; (iii) the admissible controls are merely locally ...
The optimization is defined with Sinkhorn divergence as the objective, under the non-convex and non-concave condition. This work focuses on the optimization's convergence and stability. We propose a first order sequential stochastic gradient descent ascent (SeqSGDA) algorithm. Under some mild ...