我虽然也在看Non-Convex Optimization…其实在优化领域里，关注nonconvex少说得有二十年了。 （所以真心...
As a result of that, the assumption of the concave (quasi-concave) utility function is violated too. We also introduce the possibility that compulsive eaters may have stable but nonconstant preferences. Findings Most important finding of our model is that a smooth dynamic path to addiction, ...
例如贪婪算法（Greedy Algorithm）或梯度下降法（Gradient Decent），收敛求得的局部最优解即为全局最优。
In the nonconcave case, simulation results show almost identical performance for both methods under the assumption that the dual solution is found. In contrast, the dual approach fails if the dual subproblems can only be solved to local optimality. 展开 ...
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 ...
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...
nonconcave function with singularities. A new and generic algorithm is proposed that yields a uni ed variable selection procedure. A standard error formula for estimated coef cients is obtained by using a sandwich formula. The formula is tested accurately enough for practical purposes, even when th...
Faster Non-Log-Concave Sampling via Diffusion-based Monte Carlo Abstract: Efficient sampling from complex non-log-concave distributions is a cornerstone of statistical computing and machine learning, yet it is challenged by stringen...
Non-concave optimal investment and no-arbitrage: a measure theoretical approach We consider non-concave and non-smooth random utility functions with do- main of definition equal to the non-negative half-line. We use a dynamic pro- gram... R Blanchard,L Carassus,Mikl'os R'asonyi - 《Papers...
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 ...