A unified recursion framework for stochastic variance-reduced estimation yields high-probability bounds and the first Õ(ε^{-3}) oracle complexity for stochastic optimization with expectation constraints.
hub Mixed citations
A stochastic approximation method.The annals of mathematical statistics, pages 400–407
Mixed citation behavior. Most common role is method (60%).
11
Pith papers citing it
Method
60% of classified citations
hub tools
citation-role summary
method 3
background 2
citation-polarity summary
representative citing papers
Develops quotient-categorical representations that render the average-reward distributional Bellman operator well-defined, non-expansive, and convergent under i.i.d. and Markovian sampling.
Finite-iteration guarantees are established for asynchronous scalar categorical TD in Cramér geometry and multivariate signed-categorical TD in MMD geometry under i.i.d., Markovian, and episodic sampling.
Large loss spikes in SGD are polynomially likely and serve as the dominant mechanism for escaping sharp minima toward flatter solutions in the NTK regime.
Classical momentum acceleration in mini-batch SGD for quadratics is proportional to batch size up to saturation, enabling perfect parallelization under minimal noise assumptions.
An alternative complementarity formulation for primal-dual interior-point methods keeps linear systems spectrally bounded near the solution, enabling stable single-precision solves and differentiation for bilevel and end-to-end learning.
R-SGD-Mini achieves O(1/T) convergence of expected squared gradient norm to a noise-dependent neighborhood in heavy-tailed settings by selecting the medoid gradient from M data chunks.
PSPO combines Bayesian posterior sampling of transition dynamics with constrained policy optimization to trade off generalization and robustness in offline RL.
A novel Bayesian copula-based model for joint multi-type spatio-temporal epidemic dynamics, with MCMC inference and validation on simulated data plus European meningococcal incidence records.
A market choice model with random-size sampling from past customers is represented as an elephant random walk variant, with proofs of almost sure convergence of S_n/n and regime-dependent distributional limits for scaled S_n.
A stochastic gradient algorithm learns log-optimal threshold-type strategies for online portfolio optimization across varied price dynamics.
citing papers explorer
-
Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
A unified recursion framework for stochastic variance-reduced estimation yields high-probability bounds and the first Õ(ε^{-3}) oracle complexity for stochastic optimization with expectation constraints.
-
Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
Develops quotient-categorical representations that render the average-reward distributional Bellman operator well-defined, non-expansive, and convergent under i.i.d. and Markovian sampling.
-
A Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning
Finite-iteration guarantees are established for asynchronous scalar categorical TD in Cramér geometry and multivariate signed-categorical TD in MMD geometry under i.i.d., Markovian, and episodic sampling.
-
Large Spikes in Stochastic Gradient Descent: A Large-Deviations View
Large loss spikes in SGD are polynomially likely and serve as the dominant mechanism for escaping sharp minima toward flatter solutions in the NTK regime.
-
Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration
Classical momentum acceleration in mini-batch SGD for quadratics is proportional to batch size up to saturation, enabling perfect parallelization under minimal noise assumptions.
-
A Differentiable Interior-Point Method in Single Precision
An alternative complementarity formulation for primal-dual interior-point methods keeps linear systems spectrally bounded near the solution, enabling stable single-precision solves and differentiation for bilevel and end-to-end learning.
-
Robust stochastic first order methods in heavy-tailed noise via medoid mini-batch gradient sampling
R-SGD-Mini achieves O(1/T) convergence of expected squared gradient norm to a noise-dependent neighborhood in heavy-tailed settings by selecting the medoid gradient from M data chunks.
-
Offline Policy Optimization with Posterior Sampling
PSPO combines Bayesian posterior sampling of transition dynamics with constrained policy optimization to trade off generalization and robustness in offline RL.
-
Bayesian copula-based modelling for multi-type spatio-temporal epidemic data
A novel Bayesian copula-based model for joint multi-type spatio-temporal epidemic dynamics, with MCMC inference and validation on simulated data plus European meningococcal incidence records.
-
Elephant random walk with attributed steps and extractions of random sizes
A market choice model with random-size sampling from past customers is represented as an elephant random walk variant, with proofs of almost sure convergence of S_n/n and regime-dependent distributional limits for scaled S_n.
-
Learning Threshold-Type Investment Strategies with Stochastic Gradient Method
A stochastic gradient algorithm learns log-optimal threshold-type strategies for online portfolio optimization across varied price dynamics.