Stochastic
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
arXiv:2511.19513v3 Announce Type: replace Abstract: Decentralized learning often involves a weighted global loss with heterogeneous node weights $\lambda$. We revisit two natural strategies for incorporating these weights: (i) embedding them into the local losses to retain a uniform weight (and thus a doubly stochastic matrix), and (ii) keeping the original losses while employing a $\lambda$-induced row-stochastic matrix. Although prior work shows that both strategies target the same...
Weak order one convergence of structure-preserving stochastic theta methods for stochastic differential algebraic equations with time-dependent singular matrices
new Abstract: This paper studies the weak convergence order of structure-preserving stochastic theta methods for a class of index-$1$ stochastic differential algebraic equations with time-dependent singular matrices. The singular matrix is allowed to vary in time but preserves a fixed differential-algebraic splitting, thereby extending the constant singular-matrix setting while retaining the projector structure required for constraint preservation. By exploiting the index-$1$...
Deterministic Envelopes for Tamed SGLD: Decoupling Stochastic-Gradient Noise and Localizing Taming
Announce Type: cross Abstract: Stochastic-gradient Langevin algorithms often use tamed denominators to stabilize non-globally Lipschitz drifts. This paper shows that when the denominator depends on the same stochastic-gradient realization as the numerator, the taming step changes the stochastic oracle itself and can create a stationary bias even if the original stochastic gradient is unbiased. We propose a structure-preserving framework for designing tamed denominators.
In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
Announce Type: cross Abstract: Many stochastic gradient methods are believed not to converge when the noise in stochastic gradients has only a finite $p$-th moment for $p\in\left(1,2\right)$, a setting known as the heavy-tailed noise assumption. However, some recent studies have found that Stochastic Gradient Descent ($\textsf{SGD}$), without any modification to its update rule, can surprisingly converge in expectation for convex problems with bounded domains, highlighting the potential of...
Bregman meets L\'evy: Stochastic mirror descent with heavy-tailed noise in continuous and discrete time
arXiv:2606.03769v1 Announce Type: cross Abstract: We study the robustness of stochastic mirror descent (SMD) under heavy-tailed noise, focusing on whether the method retains its convergence guarantees when run with infinite-variance stochastic gradient input. To address this question in a principled manner, we begin by introducing a continuous-time model of SMD as a stochastic differential equation (SDE) driven by a centered L\'evy noise process with finite $p$-th order moments, $1 < p \leq...
Structure-Preserving Discontinuous Galerkin Methods for Stochastic Shallow Water Equations
arXiv:2606.07155v1 Announce Type: new Abstract: Shallow water equations (SWE) are fundamental models in fluid dynamics that are essential for studying a wide range of geophysical and engineering phenomena. In many practical applications, uncertainties arising from initial conditions and bottom topography must be taken into account, motivating the development of stable and accurate numerical methods for stochastic SWE. Building on the hyperbolicity-preserving stochastic Galerkin formulation...
Residual-Controlled Multiplier Learning for Stochastic Constrained Decision-Making
arXiv:2606.07088v1 Announce Type: new Abstract: Stochastic constrained decision-making requires optimizing performance objectives while enforcing statistical requirements such as safety or fairness. However, standard primal--dual methods struggle to update multipliers robustly under stochastic mini-batch feedback, as the noise of mini-batch gradients and constraint estimates can be directly accumulated into the multiplier memory.
Dynamic Entropy Tuning in Reinforcement Learning Low-Level Quadcopter Control: Stochasticity vs Determinism
Announce Type: replace Abstract: This paper explores the impact of dynamic entropy tuning in Reinforcement Learning (RL) algorithms that train a stochastic policy. Its performance is compared against algorithms that train a deterministic one. Stochastic policies optimize a probability distribution over actions to maximize rewards, while deterministic policies select a single deterministic action per state.
Non-Asymptotic Convergence of Stochastic Iterative Algorithms: A Lyapunov Framework
arXiv:2605.31309v1 Announce Type: new Abstract: We survey Lyapunov-based techniques for the finite-time analysis of stochastic iterative algorithms, also known as stochastic approximation (SA) algorithms, for solving fixed-point equations $\bar{F}(x)=x$, where the operator $\bar{F}(\cdot)$ can only be accessed through a noisy oracle. We first focus on the standard setting in which $\bar{F}(\cdot)$ is contractive with respect to some norm and the noise is i.i.d., and explain how generalized...
Encoding neuronal shape in the stochastic dynamics of branching processes
Cell shape critically influences function, yet how complex and reproducible morphologies emerge from stochastic cellular dynamics remains unclear. Here, we investigate dendritic morphogenesis of two classes of Drosophila mechanosensory neurons with contrasting architectures, combining in vivo live imaging, quantitative analysis, cytoskeletal perturbations, and computational modeling. We show that despite sharing similar local stochastic branching rules, the two classes exhibit divergent...