Establishes maximal concentration bounds for stochastic approximation under heavy-tailed Markovian noise, with tails ranging from sub-Gaussian to heavier than Weibull depending on step sizes and contractivity properties, plus a truncation argument for unbounded noise.
The Annals of Mathematical Statistics , pages=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
M³C replaces the hard hyperparameter optimization with a sequence of simpler problems using a majorant for the log-determinant approximated via Monte Carlo, with proven high-probability convergence to a critical point under assumptions.
Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.
New MCMC methods employ data-driven similarity-driven proposals to improve sampling from posteriors on discrete state spaces, extending to hierarchical models without marginalizing latent variables.
SABRE is a simulation-based bias correction framework that reduces finite-sample bias for the parametric component and dispersion parameter in semiparametric regression models, with asymptotic bias reduction without variance inflation shown for generalized partially linear models.
citing papers explorer
-
Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise
Establishes maximal concentration bounds for stochastic approximation under heavy-tailed Markovian noise, with tails ranging from sub-Gaussian to heavier than Weibull depending on step sizes and contractivity properties, plus a truncation argument for unbounded noise.
-
A Majorization-Minimization with Monte Carlo Approach for Hyperparameter Estimation
M³C replaces the hard hyperparameter optimization with a sequence of simpler problems using a majorant for the log-determinant approximated via Monte Carlo, with proven high-probability convergence to a critical point under assumptions.
-
Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits
Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.
-
Similarity-Driven Proposals for MCMC Algorithms on Discrete Spaces
New MCMC methods employ data-driven similarity-driven proposals to improve sampling from posteriors on discrete state spaces, extending to hierarchical models without marginalizing latent variables.
-
Bias Correction for Semiparametric Regression Models
SABRE is a simulation-based bias correction framework that reduces finite-sample bias for the parametric component and dispersion parameter in semiparametric regression models, with asymptotic bias reduction without variance inflation shown for generalized partially linear models.