stochastic methods

Content tagged with stochastic methods

[W8] The global convergence time of stochastic gradient descent in non-convex landscapes: Sharp estimates via large deviations
[J46] Setwise coordinate descent for dual asynchronous decentralized optimization
[C95] Tamed Langevin sampling under weaker conditions
[J42] Quick or cheap? Breaking points in dynamic markets
[J41] A unified stochastic approximation framework for learning in games
[C94] Accelerated regularized learning in finite N-person games
[C90] What is the long-run distribution of stochastic gradient descent? A large deviations analysis
[J40] Multi-agent online learning in time-varying games
[C88] The equivalence of dynamic and strategic stability under regularized learning in games
[C87] Riemannian stochastic optimization methods avoid strict saddle points
[C83] On the convergence of policy gradient methods to Nash equilibria in general stochastic games
[C82] No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation
[C81] Pick your neighbor: Local Gauss-Southwell rule for fast asynchronous decentralized optimization
[C77] UnderGrad: A universal black-box optimization method with almost dimension-free convergence rate guarantees
[C76] Nested bandits
[C75] The dynamics of Riemannian Robbins-Monro algorithms
[J34] Minibatch forward-backward-forward methods for solving stochastic variational inequalities
[C73] Fast routing under uncertainty: Adaptive learning in congestion games with exponential weights
[C72] The convergence rate of regularized learning in games: From bandits and uncertainty to optimism and beyond
[C71] Sifting through the noise: Universal first-order methods for stochastic variational inequalities
[C70] Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements
[C66] Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information
[C65] The last-iterate convergence rate of optimistic mirror descent in stochastic variational inequalities
[C64] The limits of min-max optimization algorithms: Convergence to spurious non-critical sets
[C63] Zeroth-order non-convex learning via hierarchical dual averaging
[C62] Regret minimization in stochastic non-convex learning via a proximal-gradient approach
[J31] On the convergence of mirror descent beyond stochastic convex programming
[C60] On the almost sure convergence of stochastic gradient descent in non-convex problems
[C58] Online non-convex optimization with imperfect feedback
[C57] Explore aggressively, update conservatively: Stochastic extragradient methods with variable stepsize scaling
[C56] A new regret analysis for Adam-type algorithms
[C54] Finite-time last-iterate convergence for multi-agent learning in games
[C53] Quick or cheap? Breaking points in dynamic markets
[C51] Online and stochastic optimization beyond Lipschitz continuity: A Riemannian approach
[J27] Learning in games with continuous action sets and unknown payoff functions
[C50] On the convergence of single-call stochastic extra-gradient methods
[C48] Convergent noisy forward-backward-forward algorithms in non-monotone variational inequalities
[C44] Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile
[J26] Stochastic mirror descent dynamics and their convergence in monotone variational inequalities
[J24] On the convergence of gradient-like flows with noisy gradient input
[C39] On the convergence of stochastic forward-backward-forward algorithms with variance reduction
[C37] Distributed asynchronous optimization with unbounded delays: How slow can you go?
[J23] On the robustness of learning in games with stochastically perturbed payoff observations
[J22] Distributed stochastic optimization via matrix exponential learning
[J21] A continuous-time approach to online optimization
[C32] Stochastic mirror descent in variationally coherent optimization problems
[C28] Mirror descent learning in continuous games
[C27] Convergence to Nash equilibrium in continuous games with noisy first-order feedback
[C26] Hedging under uncertainty: regret minimization meets exponentially fast convergence
[J15] A stochastic approximation algorithm for stochastic semidefinite programming
[J13] Imitation dynamics with payoff shocks
[C24] Distributed learning for resource allocation under uncertainty
[J8] Penalty-regulated dynamics and robust learning procedures in games
[C7] Selfish Routing Revisited: Degeneracy, Evolution and Stochastic Fluctuations
[J2] The emergence of rational behavior in the presence of stochastic perturbations
[D2] Stochastic perturbations in game theory and applications to networks
[C4] Learning in the presence of noise