No article text was recorded for this version.
state-dependent noise modeling (state-dependent gradient noise)
Version 2 of 234 papers43 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Emergence of heavy tails in homogenized stochastic gradient descent
- Blog: Weight Space Probability Densities in Stochastic Learning: I. Dynamics and Equilibria
- Blog: Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity
- Blog: Computing the Bias of Constant-step Stochastic Approximation with Markovian Noise
- Blog: Multiplicative Noise and Heavy Tails in Stochastic Optimization
- Blog: Stochastic Gradient and Langevin Processes
- Blog: A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
- Blog: The alignment property of SGD noise and how it helps select flat minima: A stability analysis
- Blog: Second-Order Guarantees of Stochastic Gradient Descent in Nonconvex Optimization
- Blog: Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise
- Blog: Power-Law Escape Rate of SGD
- Blog: Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match
- Blog: Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity
- Blog: One Sample Stochastic Frank-Wolfe
- Blog: Toward Understanding the Importance of Noise in Training Neural Networks
- Blog: The Noise Geometry of Stochastic Gradient Descent: A Quantitative and Analytical Characterization
- Blog: Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
- Blog: Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization
- Blog: Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity
- Blog: Non-asymptotic Analysis of Biased Stochastic Approximation Scheme
- Blog: Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes
- Blog: Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
- Blog: Almost Sure Convergence of Stochastic Gradient Methods under Gradient Domination
- Blog: Strong error analysis for stochastic gradient descent optimization algorithms
- Blog: A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta
- Blog: Multiplicative Noise and Heavy Tails in Stochastic Optimization
- Blog: Stochastic Recursive Inclusions in Two Timescales with Nonadditive Iterate-Dependent Markov Noise
- Blog: Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization
- Blog: PCA of high dimensional random walks with comparison to neural network training
- Blog: Quasi-potential theory for escape problem: Quantitative sharpness effect on SGD's escape from local minima
- Blog: Stochastic Differential Equations for Modeling First Order Optimization Methods
- Blog: Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting
- Blog: Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise
- Blog: Power-Law Escape Rate of SGD
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_state_dependent_noise_modeling_state_dep_5f56916a,
title = {state-dependent noise modeling (state-dependent gradient noise)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/state-dependent-noise-modeling-state-dependent-gradient-noise/rdr_5f56916a18324c74a03b8c7b734f4c71},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 2, frozen text):
@misc{lacuna_state_dependent_noise_modeling_state_dep_5f56916a_v2,
title = {state-dependent noise modeling (state-dependent gradient noise)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/state-dependent-noise-modeling-state-dependent-gradient-noise/rdr_5f56916a18324c74a03b8c7b734f4c71/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-22},
}