Normalized convergence in stochastic optimization
نویسندگان
چکیده
منابع مشابه
Moment Convergence Rate in Stochastic Optimization
where X is the decision set and Q0, the distribution of ξ, is a probability distribution supported on [0, 1]. This kind of problem can be solved numerically or (in special cases) in closed form if we know the exact distribution of Q0. Unfortunately, in practice one rarely knows the exact distribution Q0. Instead, one often has only partial information about Q0, which may include limited distrib...
متن کاملConvergence of trajectories in infinite horizon optimization
In this paper, we investigate the convergence of a sequence of minimizing trajectories in infinite horizon optimization problems. The convergence is considered in the sense of ideals and their particular case called the statistical convergence. The optimality is defined as a total cost over the infinite horizon.
متن کاملOn Convergence of Evolutionary Computation for Stochastic Combinatorial Optimization
Extending Rudolph’s works on the convergence analysis of evolutionary computation (EC) for deterministic combinatorial optimization problems (COPs), this brief paper establishes a probability one convergence of some variants of explicit-averaging EC to an optimal solution and the optimal value for solving stochastic COPs.
متن کاملStochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence
In this paper, a new theory is developed for firstorder stochastic convex optimization, showing that the global convergence rate is sufficiently quantified by a local growth rate of the objective function in a neighborhood of the optimal solutions. In particular, if the objective function F (w) in the -sublevel set grows as fast as ‖w − w∗‖ 2 , where w∗ represents the closest optimal solution t...
متن کاملFinite Sample Convergence Rates of Zero-Order Stochastic Optimization Methods
• Let Ak denote the set of methods that observe a sequence of data pairs Y t = (F (θ, X ), F (τ , X )), 1 ≤ t ≤ k, and return an estimate θ̂(k) ∈ Θ. • Let FG denote the class of functions we want to optimize, where for each (F, P ) ∈ FG the subgradient g(θ;X) satisfies EP [‖g(θ;X)‖2∗] ≤ G. • For each A ∈ Ak and (F, P ) ∈ FG, consider the optimization gap: k(A, F, P,Θ) := f (θ̂(k))− inf θ∈Θ f (θ) ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Annals of Operations Research
سال: 1991
ISSN: 0254-5330,1572-9338
DOI: 10.1007/bf02204816