Diffusion and Search Dynamics

Neueste Paper

• Stochastic Resetting Accelerates Reinforcement Learning Beyond Random Search

  Jello Zhou, David J. Schwab, Vudtiwat Ngampruetikorn · 21. Juli 2026

  Stochastic resetting -- intermittently returning a process to a fixed reference state -- has emerged as an effective mechanism for optimizing first-passage properties. Existing theory largely treats processes that search but do not learn: the searcher follows fixed dynamics, accumulating no knowledg…

• One-step lowest-variance selection in a Gaussian random-field model motivated by masked diffusion: Total correlation and a square root collision threshold

  Linjun Li · 21. Juli 2026

  Motivated by confidence-guided parallel unmasking in masked discrete diffusion, we study a single selection step in a stylized Gaussian random-field model. A locally dependent nonnegative score field represents position wise uncertainty, and the scheduler selects the K positions with the smallest sc…

• Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

  Hongkun Dou, Zike Chen, Fengji Li, Hongjue Li, Yue Deng · 5. Juni 2026

  Controllable generation with discrete diffusion models is often hindered by high computational overhead or the need for retraining. In this paper, we present \underline{\textbf{G}}radient-\underline{\textbf{I}}nformed \underline{\textbf{L}}ogit \underline{\textbf{C}}orrection (\textbf{GILC}), a plug…

• Constraint-Enhanced Physical Search through Correlation Matching

  Song-Ju Kim · 4. Juni 2026

  Physical systems do not merely add noise to search processes; they impose constraints that generate structured correlations. We propose a principle of constraint-enhanced physical search in which temporal correlations in exploration are matched to constraint-induced spatial correlations in the updat…

• Ridge Regression from Poisson Resetting: A Renewal Perspective on Spectral Regularization

  Petar Jolakoski · 29. Mai 2026

  We connect stochastic resetting from non-equilibrium statistical physics with ridge regularization in statistical learning. For linear gradient flow, resetting to the origin at rate $r$ produces stationary mean $(X^\top X+rI)^{-1}X^\top y$, exactly the ridge estimator with penalty $\lambda=r$. This …

• Efficiency of Parallel and Restart Exploration Strategies in Model Free Stochastic Simulations

  Ernesto Garcia, Paola Bermolen, Matthieu Jonckheere, Seva Shneer · 7. Mai 2026

  We analyze the efficiency of parallelization and restart mechanisms for stochastic simulations in model-free settings, where the underlying system dynamics are unknown. Such settings are common in Reinforcement Learning (RL) and rare event estimation, where standard variance-reduction techniques lik…

• Almost Bayesian: The Fractal Dynamics of Stochastic Gradient Descent

  Max Hennick, Stijn De Baerdemacker · 17. März 2026

  We show that the behavior of stochastic gradient descent is related to Bayesian statistics by showing that SGD is effectively diffusion on a fractal landscape, where the fractal dimension can be accounted for in a purely Bayesian way. By doing this we show that SGD can be regarded as a modified Baye…

• Cost-Aware Diffusion Active Search

  Arundhati Banerjee, Jeff Schneider · 24. Februar 2026

  Active search for recovering objects of interest through online, adaptive decision making with autonomous agents requires trading off exploration of unknown environments with exploitation of prior observations in the search space. Prior work has proposed information gain and Thompson sampling based …

• Probabilistic Insights for Efficient Exploration Strategies in Reinforcement Learning

  Ernesto Garcia, Paola Bermolen, Matthieu Jonckheere, Seva Shneer · 16. Januar 2026

  We investigate efficient exploration strategies of environments with unknown stochastic dynamics and sparse rewards. Specifically, we analyze first the impact of parallel simulations on the probability of reaching rare states within a finite time budget. Using simplified models based on random walks…

• Using Linearized Optimal Transport to Predict the Evolution of Stochastic Particle Systems

  Nicholas Karris, Evangelos A. Nikitopoulos, Ioannis G. Kevrekidis, Seungjoon Lee, Alexander Cloninger · 18. November 2025

  We develop an Euler-type method to predict the evolution of a time-dependent probability measure without explicitly learning an operator that governs its evolution. We use linearized optimal transport theory to prove that the measure-valued analog of Euler's method is first-order accurate when the m…