Time-Sensitive Importance Splitting

arXiv:2506.19568 · cs.LO, cs.NA, math.NA · Submitted 2025-06-24 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Computer Science. The day in computer science: software, systems and theory on arXiv.

Tom: We're looking at the paper: "Time-Sensitive Importance Splitting".

Paper summary: Jane: So, to break it down, this paper proposes this new method called time-sensitive importance splitting. What is the main idea behind extending that classical idea?

Tom: They extend it by making the importance function time-sensitive. Instead of just looking at the discrete state part, they look at the lower and upper bounds of all active timers in each state to see if the target is still reachable under those time constraints.

Lu: The theoretical foundation involves analyzing timed behavior by defining a timed distance metric based on active timer values, which then creates an importance function based on that distance. It’s essentially measuring the distance from the current state to the target states using time information.

Meng: If this works, it means we can get a much finer-grained estimate of how important a state is, especially when the order in which those timers activate matters for hitting the target. That sounds like it could significantly improve precision compared to just using a standard importance function.

Lalam: The paper uses an analysis of timed behavior by characterizing reachability through state classes that encode both the discrete values and the timers, and their main contribution is adapting classical symbolic model checking analysis for forwards reachability to compute backwards reachability from those target states.

Tom: So they aren't just improving the importance function; they are using that new information to search backward from where you want to end, which is a big shift in how the simulation path is steered.

Jane: That’s interesting because it means they can actively guide the simulation towards that rare event instead of just hoping for it. It seems like they’re trying to solve the problem where the discrete state alone isn't enough information to measure distance to a target state, as mentioned in their summary.

Meng: I wonder about the computational cost here. They admit that their pre-calculations for this time-sensitive importance function are more expensive than just using only the discrete information, especially because of all those extra states they have to consider.

Lu: They suggest that these computation times remain manageable for many examples because the timing constraints can be efficiently represented by difference bound matrices, which require polynomial time in the number of timers for encoding and manipulation.

Lalam: And they also mention a future direction where they envision combining this approach with compositional importance function calculation methods to achieve both time-sensitive estimations and arbitrary scalability.

Tom: So the summary boils down to: they extend ISPLIT by incorporating timer bounds, use backwards reachability search, and it’s theoretically effective even though the pre-calculations are heavier. That’s what they claim in this paper called "Time-Sensitive Importance Splitting."

Conclusion: Jane: So, looking at the whole thing now—the paper "Time-Sensitive Importance Splitting"—what does this actually mean for someone who isn't deep into the simulation math?

Tom: In simple terms, they took a method designed for simpler models and made it smarter about time. They’re using the active timer values to tell them how important a state is, which helps them find that rare event more reliably when you have time limits on your simulation.

Lu: It means for non-Markovian systems, you don't have to rely only on the discrete state information; you can use the timing context to measure the distance to where you want to go. This directly addresses that limitation where the discrete part of a state isn't enough information <ref:2506.19568#pg2>.

Meng: For me, what matters is that they have a prototype implementation on the Modest Toolset and showed encouraging results in experiments with something like a repairable DFT example with PAND gates. That shows it’s not just theory; it’s actually runnable in practice.

Lalam: I agree, the experimental validation compared their RES-time-d runs against CMC and RES-notime, and all the time-sensitive runs produced confidence intervals that contained the ground truth probability phi. This suggests this approach can significantly increase precision for time-bounded reachability properties under different simulation budgets <ref:2506.19568#pg3>.

Jane: So, it moves us closer to being able to perform more accurate simulations of complex, real-world systems that have timing dependencies. It’s about getting better estimates when you can’t run an infinitely long simulation.

Tom: Exactly. The authors introduced time-sensitive importance splitting as a novel extension of classical ISPLIT for the importance function calculation by incorporating the timer values in estimating the distance to target states <ref:2506.19568#pg1>. It’s an automatic way to calculate this information backwards, and they showed it works with some PAND gate examples.

Lu: The paper points out that while their pre-calculations are more expensive, they envision future work combining this with compositional importance function calculation methods to handle arbitrary scalability.

Meng: The limitation they flag is that the state space explosion can still be an issue, which they plan to mitigate with compositional IF calculation methods or better duplication detection methods. That’s the trade-off right there.

Lalam: So, this paper shows a way to get better estimates for time-bounded reachability in non-Markovian models by using time information within importance splitting, even with those computational overheads they acknowledge.

Gabriel Dengler, Carlos E. Budde, Laura Carnevali, Arnd Hartmanns

Saarland University · Technical University of Denmark · Department of Information Engineering, University of Florence Department of Information Engineering, University of Florence Department of Information Engineering, University of Twente

cs.LO, cs.NA, math.NA

Submitted: 2025-06-24

Updated: 2025-06-24

Comments: Accepted at QEST+FORMATS 2025

License: http://creativecommons.org/licenses/by-sa/4.0/

Importance score: 89/100

The gist: State-of-the-art methods for rare event simulation of nonMarkovian models face practical or theoretical limits if observing the event of interest requires prior knowledge or information on the timed…

Key concepts

Time-Sensitive Importance Splitting
This is an extension of classical importance splitting that incorporates the active timer values from the system's states. Instead of just looking at the discrete state, it considers how much time remains or is relevant for reaching a target, making the importance estimation more accurate when timer order matters.
Non-Markovian Models
These are systems where future behavior depends not only on the current state but also on how long that state has been active. This complexity arises from having multiple timers in each state, which makes traditional evaluation methods much harder to apply effectively.
Timed Distance Metric (d)
This is a mathematical tool used to measure the 'distance' between states based on their active timer values. It defines how important a state is by calculating the maximum difference in these timer values, helping determine reachability within time constraints.

Terminology

Summary

State-of-the-art methods for rare event simulation of nonMarkovian models face practical or theoretical limits if observing the event of interest requires prior knowledge or information on the timed behavior of the system In this paper, we attack both limits by extending importance splitting with a time-sensitive importance function. p. 0

Where the paper says it

de 2 Technical University of Denmark, Lyngby, Denmark 3 Department of Information Engineering, University of Florence, Florence, Italy 4 University of Twente, Enschede, The Netherlands Abstract State-of-the-art methods for rare event simulation of nonMarkovian models face practical or theoretical limits if observing the event of interest requires prior knowledge or information on the timed behavior of the system. In this paper, we attack both limits by extending importance splitting with a time-sensitive importance function.

Introduction to the Problem

Quantitative evaluation methods provide model-driven guidance for the design, development, and operation of critical systems subject to RAMS requirements. While the evaluation of Markovian models leverages efficient consolidated approaches, that of non-Markovian models faces notably harder challenges. p. 0

Where the paper says it

1 Introduction Quantitative evaluation methods provide model-driven guidance for the design, development, and operation of critical systems subject to RAMS requirements [24, 39,44,52]. While the evaluation of Markovian models leverages efficient consolidated approaches [1,3,29,46], that of non-Markovian models faces notably harder challenges [26,28,54].

Analytical methods provide numerical solutions under modeling restrictions, such as at most one non-exponential timer in each state, or perform semi-symbolic state space enumeration suffering explosion issues with many concurrent non-exponential timers. p. 0
Where the paper says it

To overcome them, analytical methods provide numerical solutions under modeling restrictions, e. , at most one non-exponential timer in each state [18,27,28,51], or perform semi-symbolic state space enumeration [33], suffering explosion issues with many concurrent non-exponential timers.

Simulation remains the primary method to evaluate large non-Markovian models because it can limit the computational effort beforehand. p. 0
Where the paper says it

, at most one non-exponential timer in each state [18,27,28,51], or perform semi-symbolic state space enumeration [33], suffering explosion issues with many concurrent non-exponential timers. Despite recent advances [2,6,7,16], simulation remains the primary method to evaluate large non-Markovian models, as it can limit the computational effort beforehand.

The Proposed Solution

The authors introduce time-sensitive importance splitting, which extends classical ISPLIT by considering lower and upper bounds of active timers in each state. This allows checking if the target is still reachable not only given the discrete part of the state but also under consideration of time. p. 1

Where the paper says it

This allows us to check, e. , if the target is still reachable, not only given the discrete part of the state but also under consideration of time.

They employ an analysis of timed, but not stochastic, behavior by characterizing reachability by state classes encoding discrete values and timers. p. 1
Where the paper says it

, if the target is still reachable, not only given the discrete part of the state but also under consideration of time. To this end, we employ an analysis of the timed, but not stochastic, behavior of the system by characterizing the reachability of states (encoding discrete values and timers) by state classes (SCs) [53].

A main contribution is adapting classical SC analysis for forwards reachability from the initial state to compute backwards reachability from the target states. p. 1
Where the paper says it

To this end, we employ an analysis of the timed, but not stochastic, behavior of the system by characterizing the reachability of states (encoding discrete values and timers) by state classes (SCs) [53]. As one of our main contributions, we show how classical SC analysis for forwards reachability from the initial state can be adapted to compute backwards reachability from the target states.

Theoretical Foundation of Time-Sensitive IF

The approach is simple because during simulation it only requires replacing the time-agnostic IF with a time-sensitive IF. This method is effective because it provides a finer-grained estimation of how important a state is, especially when the order of timers is relevant to reach a target state. p. 1

Where the paper says it

5 for the latter). – It is effective, because it provides a finer-grained estimation of how important a state is, which is especially apparent if the order of timers is relevant to reach a target state.

The computation for the time-sensitive IF involves analyzing the timed behavior by defining a timed distance metric d: S → N0 based on active timer values. p. 6
Where the paper says it

Timed distance metric. We define the timed distance metric d : S → N0 of a state s ∈ S as the distance of s to the target given the value of the active timers in s (rather than as a distance d : L → N0 based solely on the location of s).

This distance metric is used to obtain an IF f(s) = maxs′∈S d(s′) − d(s). p. 6
Where the paper says it

We define the timed distance metric d : S → N0 of a state s ∈ S as the distance of s to the target given the value of the active timers in s (rather than as a distance d : L → N0 based solely on the location of s). Thus, we obtain as IF f : S → N0 with f(s) = f(⟨l, τ ⟩) = maxs ′∈S {d(s ′ )} − d(s) = maxs ′∈S {d(s ′ )} − d(⟨l, τ ⟩).

Experimental Validation

Preliminary experiments show the potential of the approach in estimating rare event probabilities for an example from reliability engineering. The experimental results compared RES-time-d runs against CMC and RES-notime, showing that all RES-time-d cases managed to produce CIs that contain the ground truth φ. p. 4

Where the paper says it

When the event of interest occurs with low probability, though, computing precise CIs needs infeasibly many samples [49]. RES can alleviate this, e.

This demonstrates how the time-sensitive IF can help in practical scenarios to significantly increase the precision of estimates for time-bounded reachability properties under different simulation time budgets. p. 0
Where the paper says it

de 2 Technical University of Denmark, Lyngby, Denmark 3 Department of Information Engineering, University of Florence, Florence, Italy 4 University of Twente, Enschede, The Netherlands Abstract State-of-the-art methods for rare event simulation of nonMarkovian models face practical or theoretical limits if observing the event of interest requires prior knowledge or information on the timed behavior of the system. In this paper, we attack both limits by extending importance splitting with a time-sensitive importance function.

Future Directions and Limitations

The discussion highlights potential limitations such as state space explosion, which can be mitigated by compositional IF calculation methods or improved duplication detection methods. The authors also note that incorporating a global timer tage could help in a time-bounded setting to know whether the target can still be reached given the time bound. p. 9

Where the paper says it

The semantics of this nonMarkovian system becomes fully stochastic when given in terms of an IOSA [40]. We study the transient property of observing a system failure before 1248 time units: φ = Pr(TLE | tage ≤ 1248), where tage denotes the global system time.

Future work plans include realizing ideas to tackle shortcomings like state space explosion and studying backwards reachability for other model classes such as STA or hybrid systems. p. 1
Where the paper says it

While the method of [23], using first enumeration of stochastic state classes (SSCs) [33] and then MC simulation, can theoretically tackle these cases, it only works when the critical event happens near the root of the state-space. Furthermore, transient analysis with SSCs may suffer state space explosion and numerical issues for large and stiff models.

Conclusion

In this paper, we introduced time-sensitive importance splitting as a novel extension of classical ISPLIT for the IF calculation, which incorporates the timer values in estimating the distance to the target states. Based on existing theory of SCs, we presented an automatic way to calculate this information in a backwards reachability manner. p. 6

Where the paper says it

Thus, we obtain as IF f : S → N0 with f(s) = f(⟨l, τ ⟩) = maxs ′∈S {d(s ′ )} − d(s) = maxs ′∈S {d(s ′ )} − d(⟨l, τ ⟩). To calculate our distance metric d, we use the theory of SCs and effectively run the analysis backwards from the target locations.

We implemented a prototype upon the Modest Toolset. p. 0
Where the paper says it

To this end, we perform backwards reachability search from the target states, considering information about the lower and upper bounds of the active timers in order to steer the generation of paths towards the rare event. We have developed a prototype implementation of the approach for input/output stochastic automata within the Modest Toolset.

The empirical evaluation based on a repairable DFT example with PAND gates demonstrated very encouraging results. p. 9
Where the paper says it

2 Experimental Support in the Modest Toolset We have extended the Modest Toolset [30] to parse repairable DFT models written in Kepler, and compute time-sensitive IFs from models with stochastic timed semantics. With the exception of SPARE-gates and -BEs, the new support for repairable DFTs covers all gates from [13,40], including dynamic gates such as PAND (pand in Kepler) and functional dependence (fdep), as well as priorityordered repair boxes (rbox prio).

References

Budde, C.E., D’Argenio, P.R., Hartmanns, A., Sedwards, S.: An efficient statistical model checker for nondeterminism and rare events

Dengler, G., Carnevali, L., Budde, C.E., Vicario, E.: Transient evaluation of nonMarkovian models by stochastic state classes and simulation

Budde, C.E., D’Argenio, P.R., Monti, R.E., Stoelinga, M.: A compositional semantics for Repairable Fault Trees with general distributions

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Budde, C.E., D’Argenio, P.R., Hermanns, H.: Rare event simulation with fully automated importance splitting

Dengler, G., Carnevali, L., Budde, C.E., Vicario, E.: Transient evaluation of nonMarkovian models by stochastic state classes and simulation

Budde, C.E., D’Argenio, P.R., Monti, R.E., Stoelinga, M.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., Remke, A.: Symbolic state-space exploration meets statistical model checking

Dengler, G., Carnevali, L., Budde, C.E., Vicario, E.: Transient evaluation of nonMarkovian models by stochastic state classes and simulation

Budde, C.E., D’Argenio, P.R., Monti, R.E.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Budde, C.E., D’Argenio, P.R., Hermanns, H.: Rare event simulation with fully automated importance splitting

Dengler, G., Carnevali, L., Budde, C.E., Vicario, E.: Transient evaluation of nonMarkovian models by stochastic state classes and simulation

Budde, C.E., D’Argenio, P.R., Monti, R.E., Stoelinga, M.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., Remke, A.: Symbolic state-space exploration meets statistical model checking

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., Remke, A.: Symbolic state-space exploration meets statistical model checking

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting

Henzinger, T.A., Nicollin, X., Sifakis, J., Yovine, S.: Symbolic model checking for realtime systems

Monti, R.E., Budde, C.E., D’Argenio, P.R.: A compositional semantics for Repairable Fault Trees with general distributions

Niehage, M., da Silva, C., Remke, A., Hartmanns, A.: Rare event simulation for stochastic hybrid systems using symbolic importance functions

Budde, C.E., D’Argenio, P.R., Hartmanns, A.: Automated compositional importance splitting <ref:2506. p. 2

Where the paper says it

As discussed in Sec. 5, we envision that, in future work, we can achieve both time-sensitive importance estimations and arbitrary scalability by combining our approach with compositional IF calculation methods from the literature [9,11].

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Time-sensitive importance splitting allows AI systems to estimate rare event probabilities for nonMarkovian models by considering lower and upper bounds of the active timers in each state. This enables checking if the target is still reachable, not only given the discrete part of the state but also under consideration of time.

  2. The improved system can automatically derive a time-sensitive importance function that explicitly considers concrete valuations of stochastic timers, which is crucial when the order of timers is relevant to reach a target state in models like DFT with PAND gates.

  3. The approach enables the estimation of a finer-grained importance metric for ISPLIT by employing backwards reachability search from the target states, considering information about the lower and upper bounds of the active timers.

  4. The system can be adapted to compute backwards reachability from target states by leveraging classical state class analysis, providing a method that is the first one to incorporate continuous timer information based on backwards reachability search to provide a finer-grained importance metric for ISPLIT.

  5. The improved AI system can handle time-bounded properties, such as estimating Pr(TLE tage ≤ 1248), by incorporating a global timer tage that allows extraction of the minimum and maximum time needed until reaching the target.

  6. The system can be extended to handle unbounded timer supports by using the actual bound [0, infinity) in backwards state class calculations, addressing limitations where rare event depends on heavy tails in continuous random variables.

Abstract

State-of-the-art methods for rare event simulation of non-Markovian models face practical or theoretical limits if observing the event of interest requires prior knowledge or information on the timed behavior of the system. In this paper, we attack both limits by extending importance splitting with a time-sensitive importance function. To this end, we perform backwards reachability search from the target states, considering information about the lower and upper bounds of the active timers in order to steer the generation of paths towards the rare event. We have developed a prototype implementation of the approach for input/output stochastic automata within the Modest Toolset. Preliminary experiments show the potential of the approach in estimating rare event probabilities for an example from reliability engineering.

Sources

Related papers