variance reduction

A Difference-in-Difference Approach to Detecting AI-Generated Images CVPR 2026 A Single-Loop Stochastic Proximal Quasi-Newton Method for Large-Scale Nonsmooth Convex Optimization JMLR 2026 Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning AAAI 2026 Conditional neural control variates for variance reduction in Bayesian inverse problems UAI 2026 Conformal Risk Minimization with Variance Reduction UAI 2026 Decentralized Non-convex Stochastic Optimization with Heterogeneous Variance AAAI 2026 Efficient Weighted Sampling via Score-based Generative Models CVPR 2026 Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite UAI 2026 Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models WACV 2026 Improving Value-based Process Verifier via Low-Cost Variance Reduction AAAI 2026 KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation EACL 2026 LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models ACL 2026 Online Convex Optimization with Sublinear Noisy Probes COLT 2026 Online Learning for Project Selection in Hedonic Project Games UAI 2026 Reusing Samples in Variance Reduction ALT 2026 Stabilizing Policy Gradient Methods via Reward Profiling AAAI 2026 Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method ALT 2026 Variance reduction combining pre-experiment and in-experiment data CLeaR 2026 Variance Reduction for Non-Log-Concave Sampling with Applications to Inverse Problems UAI 2026 Variance Reduction via Resampling and Experience Replay AAAI 2026 Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity AAAI 2025 A Coefficient Makes SVRG Effective ICLR 2025 Active Learning with Selective Time-Step Acquisition for PDEs ICML 2025 Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback JMLR 2025 Dependent Randomized Rounding for Budget Constrained Experimental Design UAI 2025