conftrace_

convergence rate

607 papers

Explore in graph

Co-occurring keywords

stochastic gradient descent (1091) convex optimization (1321) stochastic optimization (1060) gradient descent (1144) convergence analysis (395) non-convex optimization (547) nonconvex optimization (316) variance reduction (523) stochastic gradient (296) learning theory (519)

Papers

Super-Acceleration with Cyclical Step-sizes AISTATS 2022
Beyond black box densities: Parameter learning for the deviated components NIPS 2022
Convergence Guarantees for the Good-Turing Estimator JMLR 2022
Single Loop Gaussian Homotopy Method for Non-convex Optimization NIPS 2022
Randomized Stochastic Gradient Descent Ascent AISTATS 2022
The EM Algorithm is Adaptively-Optimal for Unbalanced Symmetric Gaussian Mixtures JMLR 2022
Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms AISTATS 2022
Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings AAAI 2022
Extragradient Method: O(1/K) Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity AISTATS 2022
Adaptive and Universal Algorithms for Variational Inequalities with Optimal Convergence AAAI 2022
Provable Tensor-Train Format Tensor Completion by Riemannian Optimization JMLR 2022
Understanding and mitigating the limitations of prioritized experience replay UAI 2022
On the Convergence Rates of Policy Gradient Methods JMLR 2022
Statistical, Robustness, and Computational Guarantees for Sliced Wasserstein Distances NIPS 2022
Faster Perturbed Stochastic Gradient Methods for Finding Local Minima ALT 2022
Stochastic Whitening Batch Normalization CVPR 2021
Towards Understanding the Spectral Bias of Deep Learning IJCAI 2021
Loop Estimator for Discounted Values in Markov Reward Processes AAAI 2021
Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness ICML 2021
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets ICML 2021
Data Augmentation for Text Generation Without Any Augmented Data IJCNLP 2021
A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning NIPS 2021
Momentum Centering and Asynchronous Update for Adaptive Gradient Methods NIPS 2021
PID Accelerated Value Iteration Algorithm ICML 2021
First-Order Methods for Wasserstein Distributionally Robust MDP ICML 2021