conftrace_

variance reduction

523 papers

Explore in graph

Also known as

VR

Co-occurring keywords

stochastic optimization (1060) stochastic gradient descent (1091) stochastic gradient (296) reinforcement learning (4352) policy gradient (520) nonconvex optimization (316) gradient estimation (150) non-convex optimization (547) importance sampling (318) control variate (54)

Papers

Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems NIPS 2023
SLIQ: Quantum Image Similarity Networks on Noisy Quantum Computers AAAI 2023
Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making NIPS 2023
Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis NIPS 2023
Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator ICML 2023
Blockwise Stochastic Variance-Reduced Methods with Parallel Speedup for Multi-Block Bilevel Optimization ICML 2023
Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick NIPS 2023
Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time NIPS 2023
Debiasing Conditional Stochastic Optimization NIPS 2023
Stochastic Variance Reduction for Variational Inequality Methods COLT 2022
Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology ICML 2022
FedNest: Federated Bilevel, Minimax, and Compositional Optimization ICML 2022
Faster non-convex federated learning via global and local momentum UAI 2022
Markovian Interference in Experiments NIPS 2022
Shifted compression framework: generalizations and improvements UAI 2022
Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions NIPS 2022
The Role of Baselines in Policy Gradient Optimization NIPS 2022
A Unifying Framework for Variance-Reduced Algorithms for Findings Zeroes of Monotone operators JMLR 2022
Efficient Variance Reduction for Meta-learning ICML 2022
Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots ICML 2022
Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction ICML 2022
Stochastic Reweighted Gradient Descent ICML 2022
Private Streaming SCO in $\ell_p$ geometry with Applications in High Dimensional Online Decision Making ICML 2022
QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning AISTATS 2022
Learning Optimal Flows for Non-Equilibrium Importance Sampling NIPS 2022