On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

9 results for “FSM”

Re-understanding Finite-State Representations of Recurrent Policy Networkscs.LG

New approach to understand recurrent policies as FSMs without minimization.

problem Minimization of FSMs obscures the semantics of policy decisions.

method Start with unminimized FSM, apply interpretable reductions, use attention tool.

result Reveals insights into policy decisions not previously noticed.

Recurrent Policies Finite-State Machines Attention Control Policies Atari Games

2020-06-06abs ↗pdf ↗

Concept and the implementation of a tool to convert industry 4.0 environments modeled as FSM to an OpenAI Gym wrappercs.LG

Tool converts industrial systems to RL environments for optimization.

problem Lack of RL methods for optimizing industrial systems.

method Develops a tool to convert FSM models to OpenAI Gym wrappers.

result Traditional RL methods can be applied to industrial systems.

Industry 4.0 Reinforcement Learning FSM OpenAI Gym Optimization

2020-06-29abs ↗pdf ↗

Causal invariant geographic network representations with feature and structural distribution shiftscs.LG

Proposes FSM-IRL to learn invariant network representations considering feature and structural shifts.

problem Spatial heterogeneity and temporal dynamics lead to OOD generalization issues in geographic networks.

method Introduces FSM-IRL model that accounts for feature and structural distribution shifts using causal attention and reweighting.

result Demonstrates strong learning capabilities on geographic and social network datasets in OOD scenarios.

geographic networks invariant representations feature distribution shifts structural distribution shifts causal attention

2025-03-25abs ↗pdf ↗

Efficiently Vectorized MCMC on Modern Acceleratorscs.MS

This work optimizes MCMC algorithms for modern accelerators without synchronization overheads.

problem Synchronization overheads in vectorized MCMC algorithms.

method Designing single-chain MCMC algorithms as finite state machines (FSMs) to avoid synchronization.

result Achieves up to an order of magnitude speed-up in experiments.

MCMC Finite State Machines Vectorization Elliptical Slice Sampling HMC-NUTS

2025-03-20abs ↗pdf ↗

Computationally Efficient CFD Prediction of Bubbly Flow using Physics-Guided Deep Learningphysics.comp-ph

To realize efficient computational fluid dynamics (CFD) prediction of two-phase flow, a multi-scale framework was proposed in this paper by applying a physics-guided data-driven approach. Instrumental to this framework, Feature Similarity Measurement (FSM) technique was developed for error estimation in two-phase flow …

2019-10-17abs ↗pdf ↗

Score-fPINN: Fractional Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker-Planck-Levy Equationscs.LG

Score-fPINN tackles high-dimensional FPL equations using fractional score functions.

problem High-dimensional Fokker-Planck-Lévy equations with non-Brownian processes.

method Fractional score function and Physics-informed neural networks (PINN) to solve CoD and numerical overflow.

result Effective solution to high-dimensional FPL equations without fractional Laplacian.

Physics-informed neural networks Fractional score function Fokker-Planck-Lévy equations Non-Brownian processes Curse of dimensionality

2024-06-17abs ↗pdf ↗

Filter Methods for Feature Selection in Supervised Machine Learning Applications -- Review and Benchmarkcs.LG

Review and benchmark 58 feature selection methods for ML applications.

problem Selecting appropriate features for predictive modeling in ML applications.

method Synthesizes literature on feature selection benchmarking and evaluates 58 methods.

result Well-performing candidate methods identified: random forest, DISR, JIM.

feature selection machine learning filter methods benchmarking random forest

2021-11-23abs ↗pdf ↗

Distance and Equivalence between Finite State Machines and Recurrent Neural Networks: Computational resultscs.LG

Study shows challenges in converting RNNs to FSMs due to computational complexity.

problem Understanding the equivalence and distance between RNNs and FSMs.

method Computational proofs for equivalence and distance problems between RNNs and FSMs.

result Undecidability and hardness of approximation problems between RNNs and FSMs.

Finite State Machines Recurrent Neural Networks Computational Complexity Undecidability Equivalence Problem

2020-04-01abs ↗pdf ↗

Rule-based Evolving Fuzzy System for Time Series Forecasting: New Perspectives Based on Type-2 Fuzzy Sets Measures Approachstat.ML

Enhanced fuzzy system predicts chaotic time series with improved accuracy.

problem Forecasting chaotic time series with high uncertainty.

method Combines evolving fuzzy systems, participatory learning, KRLS, and type-2 fuzzy sets.

result Proposed model outperforms other methods in accuracy and complexity.

chaotic time series fuzzy systems type-2 fuzzy sets forecasting evolving fuzzy systems

2025-02-05abs ↗pdf ↗