Controlling Uncertainty of Empirical First-Passage Times in the Small-Sample Regime

Abstract

We derive general bounds on the probability that the empirical first-passage time ${\overline{\tau }}_n\equiv {\sum }_{i=1}^n{\tau }_i/n$ of a reversible ergodic Markov process inferred from a sample of $n$ independent realizations deviates from the true mean first-passage time by more than any given amount in either direction. We construct non-asymptotic confidence intervals that hold in the elusive small-sample regime and thus fill the gap between asymptotic methods and the Bayesian approach that is known to be sensitive to prior belief and tends to underestimate uncertainty in the small-sample setting. We prove sharp bounds on extreme first-passage times that control uncertainty even in cases where the mean alone does not sufficiently characterize the statistics. Our concentration-of-measure-based results allow for model-free error control and reliable error estimation in kinetic inference, and are thus important for the analysis of experimental and simulation data in the presence of limited sampling.

Revised version, contains new bounds on extreme first-passage time and additional illustrative examples

References in corpus (36)

• First-passage times in complex scale-invariant media
• First Passage Under Restart
• First order transition for the optimal search time of Lévy flights with resetting
• Optimal mean first-passage time for a Brownian searcher subjected to resetting: experimental and theoretical results
• Stability of adhesion clusters under constant force
• Simple bounds on fluctuations and uncertainty relations for first-passage times of counting observables
• Mean first-passage times of non-Markovian random walkers in confinement
• First passages for a search by a swarm of independent random searchers
• Fundamental Bounds on First Passage Time Fluctuations for Currents
• Strong defocusing of molecular reaction times results from an interplay of geometry and reaction control
• Occupation times of random walks in confined geometries: From random trap model to diffusion limited reactions
• Activated escape of a self-propelled particle from a metastable state
• Universal survival probability for a $d$-dimensional run-and-tumble particle
• Mortality, Redundancy, and Diversity in Stochastic Search
• First detected arrival of a quantum walker on an infinite line
• Record statistics and persistence for a random walk with a drift
• Plasticity of hydrogen bond networks regulates mechanochemistry of cell adhesion complexes
• Simulating rare events using a Weighted Ensemble-based string method
• First passage time statistics for two-channel diffusion
• Persistence in nonequilibrium surface growth
• The first-passage area for drifted Brownian motion and the moments of the Airy distribution
• Stochastic Dynamics of Nanoparticle and Virus Uptake
• Extreme value statistics of ergodic Markov processes from first passage times in the large deviation limit
• A Bernstein-Von Mises Theorem for discrete probability distributions
• First-passage Brownian functionals with stochastic resetting
• Estimating Entropy Production Rates with First-Passage Processes
• Infinite family of persistence exponents for interface fluctuations
• First hitting times to intermittent targets
• Statistics of the first passage time of Brownian motion conditioned by maximum value or area
• Sampling Time Effects for Persistence and Survival in Step Structural Fluctuations
• Active Brownian Particles in a Circular Disk with an Absorbing Boundary
• Protein recruitment through indirect mechanochemical interactions
• First Invader Dynamics in Diffusion-Controlled Absorption
• Concentration Inequalities for Output Statistics of Quantum Markov Processes
• First detection of threshold crossing events under intermittent sensing
• First-passage times in complex energy landscapes: a case study with nonmuscle myosin II assembly

Cited by in corpus (7)

• Restart uncertainty relation for monitored quantum dynamics
• Entropy estimation for partially accessible Markov networks based on imperfect observations: Role of finite resolution and finite statistics
• Inferring intermediate states by leveraging the many-body Arrhenius law
• Mutual Linearity is a Generic Property of Steady-State Markov Networks
• Concentration of Empirical First-Passage Times
• Fractionally Quantized Recurrence Detection Times in Monitored Quantum Many-Body Systems
• Intermediate time scale in the first product formation time distribution of Michaelis-Menten kinetics with inhibitors