← Keywords

global convergence

111 papers

Explore in graph

Co-occurring keywords

policy gradient (518) non-convex optimization (546) gradient descent (1143) stochastic gradient descent (1088) neural network (6616) neural network optimization (1293) convergence rate (606) convex optimization (1320) sample complexity (1158) expectation maximization (254)

Papers

Stochastic Gradient Succeeds for Bandits ICML 2023
On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms NIPS 2023
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies ICML 2023
On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization ICML 2023
Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees AISTATS 2023
Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron COLT 2023
On the Convergence of Gradient Flow on Multi-layer Linear Models ICML 2023
Leveraging the two-timescale regime to demonstrate convergence of neural networks NIPS 2023
Coordinate Descent Methods for Fractional Minimization ICML 2023
Global Convergence of Over-parameterized Deep Equilibrium Models AISTATS 2023
Federated Learning with Bilateral Curation for Partially Class-Disjoint Data NIPS 2023
Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization JMLR 2023
Global Convergence of Two-Timescale Actor-Critic for Solving Linear Quadratic Regulator AAAI 2023
Preconditioning Matters: Fast Global Convergence of Non-convex Matrix Factorization via Scaled Gradient Descent NIPS 2023
On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures ICML 2023
Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms AISTATS 2022
On the Global Optimum Convergence of Momentum-based Policy Gradient AISTATS 2022
A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning AISTATS 2022
Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks NIPS 2022
Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods AAAI 2022
Global Convergence and Stability of Stochastic Gradient Descent NIPS 2022
Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential NIPS 2022
Globally Convergent Policy Search for Output Estimation NIPS 2022
On ADMM in Deep Learning: Convergence and Saturation-Avoidance JMLR 2021
Softmax Policy Gradient Methods Can Take Exponential Time to Converge COLT 2021