Continuous-Time Discounted Mirror Descent Dynamics in Monotone Concave Games
نویسندگان
چکیده
We consider concave continuous-kernel games characterized by monotonicity properties and propose discounted mirror descent type dynamics. introduce two classes of dynamics whereby the associated map is constructed based on a strongly convex or Legendre regularizer. Depending regularizer, we show that these new can converge asymptotically in with merely monotone (negative) pseudogradient. Furthermore, when regularizer enjoys strong convexity, resulting even hypomonotone pseudogradient, which corresponds to shortage monotonicity.
منابع مشابه
Accelerated Stochastic Mirror Descent: From Continuous-time Dynamics to Discrete-time Algorithms
We present a new framework to analyze accelerated stochastic mirror descent through the lens of continuous-time stochastic dynamic systems. It enables us to design new algorithms, and perform a unified and simple analysis of the convergence rates of these algorithms. More specifically, under this framework, we provide a Lyapunov function based analysis for the continuous-time stochastic dynamic...
متن کاملAccelerated Mirror Descent in Continuous and Discrete Time
We study accelerated mirror descent dynamics in continuous and discrete time. Combining the original continuous-time motivation of mirror descent with a recent ODE interpretation of Nesterov’s accelerated method, we propose a family of continuous-time descent dynamics for convex functions with Lipschitz gradients, such that the solution trajectories converge to the optimum at a O(1/t2) rate. We...
متن کاملAccelerated Mirror Descent In Continuous and Discrete Time Supplementary material , NIPS 2015
1 Mirror operator ∇ψ * In this section, we discuss properties of distance generating functions and their subdif-ferentials. Let ψ be a proper, closed, convex function, and suppose that X is the effective domain of ψ (i.e. X = {x ∈ R n : ψ(x) < ∞}). The subdifferential of ψ at x ∈ X is ∂ψ(x) = {z ∈ E * : ψ(y) − ψ(x) − z, y − x ≥ 0 ∀y ∈ X }.
متن کاملStochastic Gradient Descent in Continuous Time
We consider stochastic gradient descent for continuous-time models. Traditional approaches for the statistical estimation of continuous-time models, such as batch optimization, can be impractical for large datasets where observations occur over a long period of time. Stochastic gradient descent provides a computationally efficient method for such statistical learning problems. The stochastic gr...
متن کاملDiscounted Stochastic Games
We give an alternative proof to a result of Mertens and Parthasarathy, stating that every n-player discounted stochastic game with general setup, and with a norm-continuous transition, has a subgame perfect equilibrium. † Institute of Mathematics and Center for Rationality and Interactive Decision Theory, The Hebrew University, Givat Ram, 91904 Jerusalem, Israel. e-mail: [email protected] ...
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: IEEE Transactions on Automatic Control
سال: 2021
ISSN: ['0018-9286', '1558-2523', '2334-3303']
DOI: https://doi.org/10.1109/tac.2020.3045094