Empirical evaluation of normalizing flows in Markov chain Monte Carlo

Nabergoj, David (avtor), Štrumbelj, Erik (avtor)

Recent advances in MCMC use normalizing flows to precondition target distributions and enable jumps to distant regions. However, there is currently no systematic comparison of different normalizing flow architectures for MCMC. As such, many works choose simple flow architectures that are readily available and do not consider other models. Guidelines for choosing an appropriate architecture would reduce analysis time for practitioners and motivate researchers to take the recommended models as foundations to be improved. We provide the first such guideline by extensively evaluating many normalizing flow architectures on various flow-based MCMC methods and target distributions. When the target density gradient is available, we show that flow-based MCMC outperforms classic MCMC for suitable NF architecture choices with minor hyperparameter tuning. When the gradient is unavailable, flow-based MCMC wins with off-the-shelf architectures. We find contractive residual flows to be the best general-purpose models with relatively low sensitivity to hyperparameter choice. We also provide various insights into normalizing flow behavior within MCMC when varying their hyperparameters, properties of target distributions, and the overall computational budget.

• Jezik: Angleški jezik
• Ključne besede: normalizing flow, Markov chain Monte Carlo, comparison, sampling, simulation study
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FRI - Fakulteta za računalništvo in informatiko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2025
• Št. strani: 50 str.
• Številčenje: Vol. 114, iss. 12, art. 282
• PID: 20.500.12556/RUL-176286
• UDK: 519.245:004.8
• ISSN pri članku: 0885-6125
• DOI: 10.1007/s10994-025-06900-3
• COBISS.SI-ID: 258064387
• Datum objave v RUL: 26.11.2025

Gradivo je del revije

• Naslov: Machine learning
• Skrajšan naslov: Mach. learn.
• Založnik: Kluwer Academic Publishers
• ISSN: 0885-6125
• COBISS.SI-ID: 2623527

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: normalizacijski tok, Metode Monte Carlo markovske verige, primerjava, vzorčenje, simulacijska študija

Projekti

• Financer: ARIS - Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije
• Številka projekta: P2-0442-2023
• Naslov: Podatkovne vede in digitalna preobrazba