Online convex optimization in the bandit setting: gradient descent without a gradient
From MaRDI portal
Recommendations
Cited in
(only showing first 100 items - show all)- Logarithmic regret algorithms for online convex optimization
- Perspectives on multiagent learning
- Warranty optimization in a dynamic environment
- Parallel distributed block coordinate descent methods based on pairwise comparison oracle
- Learning in games with continuous action sets and unknown payoff functions
- Exploratory distributions for convex functions
- Accelerating reinforcement learning with a directional-Gaussian-smoothing evolution strategy
- A new one-point residual-feedback oracle for black-box learning and control
- Derivative-free optimization over multi-user MIMO networks
- Distributed online bandit optimization under random quantization
- Noisy zeroth-order optimization for non-smooth saddle point problems
- A theoretical and empirical comparison of gradient approximations in derivative-free optimization
- Predictive online convex optimization
- Smoothed functional-based gradient algorithms for off-policy reinforcement learning: a non-asymptotic viewpoint
- Regret bounded by gradual variation for online convex optimization
- Analysis of Hannan consistent selection for Monte Carlo tree search in simultaneous move games
- Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
- Random gradient-free minimization of convex functions
- Online linear optimization and adaptive routing
- On two continuum armed bandit problems in high dimensions
- Minimax efficient finite-difference stochastic gradient estimators using black-box function evaluations
- Decentralized online convex optimization based on signs of relative states
- Personalized optimization with user's feedback
- A mixed finite differences scheme for gradient approximation
- Online strongly convex optimization with unknown delays
- Zeroth-order feedback optimization for cooperative multi-agent systems
- Complexity guarantees for an implicit smoothing-enabled method for stochastic MPECs
- Event-triggered distributed online convex optimization with delayed bandit feedback
- Non-stationary stochastic optimization
- Truthful mechanisms with implicit payment computation
- The data-driven newsvendor problem: new bounds and insights
- Online sequential optimization with biased gradients: theory and applications to censored demand
- No regret learning in oligopolies: Cournot vs. Bertrand
- Perturbation techniques in online learning and optimization
- Generalized mirror descents in congestion games
- Better algorithms for benign bandits
- Online learning to rank with top-k feedback
- Learning Theory
- Derivative-free methods for policy optimization: guarantees for linear quadratic systems
- Robust Power Management via Learning and Game Design
- Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise
- Preference-based online learning with dueling bandits: a survey
- Bandit convex optimization in non-stationary environments
- On gradient-based learning in continuous games
- Finite Difference Gradient Approximation: To Randomize or Not?
- Zeroth-order regularized optimization (ZORO): approximately sparse gradients and adaptive sampling
- An accelerated method for derivative-free smooth stochastic convex optimization
- Portfolio selection algorithm under financial crisis: a case study with Bursa Malaysia
- Continuous Assortment Optimization with Logit Choice Probabilities and Incomplete Information
- Technical note: Nonstationary stochastic optimization under \(L_{p,q} \)-variation measures
- Data-driven decisions for problems with an unspecified objective function
- Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
- Black-box reductions for zeroth-order gradient algorithms to achieve lower query complexity
- Derivative-free optimization methods
- Partial monitoring -- classification, regret bounds, and algorithms
- Interior-Point Methods for Full-Information and Bandit Online Learning
- Stochastic convex optimization with bandit feedback
- Logarithmic Regret Algorithms for Online Convex Optimization
- An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions
- Algorithmic Learning Theory
- A Linearly Convergent Variant of the Conditional Gradient Algorithm under Strong Convexity, with Applications to Online and Stochastic Optimization
- Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
- Zeroth-order optimization with orthogonal random directions
- Gradient-free federated learning methods with l₁ and l₂-randomization for non-smooth convex stochastic optimization problems
- Online distributed detection of sensor networks with delayed information
- Distributed online bandit linear regressions with differential privacy
- Online bandit convex optimisation with stochastic constraints via two-point feedback
- On poisoned Wardrop equilibrium in congestion games
- Decentralized online convex optimization with compressed communications
- Nonsmooth optimization by Lie bracket approximations into random directions
- Stochastic Saddle Point Problems with Decision-Dependent Distributions
- Online distributed dual averaging algorithm for multi-agent bandit optimization over time-varying general directed networks
- Distributed bandit online optimisation for energy management in smart grids
- Recent Theoretical Advances in Non-Convex Optimization
- Distributed zeroth-order optimization: convergence rates that match centralized counterpart
- Adversarial bandits with knapsacks
- Nonlinear optimization filters for stochastic time-varying convex optimization
- Adaptive control using stochastic approach for unknown but bounded disturbances and its application in balancing control
- Gradient-free algorithms for distributed online convex optimization
- Stochastic adversarial noise in the ``black box optimization problem
- Distributed constrained online convex optimization with adaptive quantization
- On the global complexity of a derivative-free Levenberg-Marquardt algorithm via orthogonal spherical smoothing
- Distributed online optimization subject to long-term constraints and time-varying topology: an event-triggered and bandit feedback approach
- Online non-monotone diminishing return submodular maximization in the bandit setting
- Estimation of several parameters in discretely-observed stochastic differential equations with additive fractional noise
- Stochastic zeroth order descent with structured directions
- Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods
- Towards data auctions with externalities
- Model-agnostic Hessian-free meta-policy optimization via zeroth-order estimation: a linear quadratic regulator perspective
- Optimization on a finer scale: bounded local subgradient variation perspective
- A stochastic quasi-Newton method in the absence of common random numbers
- Stochastic approximation and reinforcement learning: the interface and a little beyond
- Inexact zeroth-order nonsmooth and nonconvex stochastic composite optimization and applications
- A payoff-based policy gradient method in stochastic games with long-run average payoffs
- A simple and improved algorithm for noisy, convex, zeroth-order optimisation
- Distributed mirror descent for online bandit saddle point problem
- Policy gradient converges to the globally optimal policy for nearly linear-quadratic regulators
- Stochastic approach for price optimization problems with decision-dependent uncertainty
- Accelerated zero-order SGD under high-order smoothness and overparameterized regime
- Convergence analysis for a nonlocal gradient descent method via directional Gaussian smoothing
This page was built for publication: Online convex optimization in the bandit setting: gradient descent without a gradient
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2921693)
