AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Deep Optimal Stopping

Sebastian Becker, Patrick Cheridito, Arnulf Jentzen

JMLR 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 149 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train stopping decisions on (X_n, g(n,X_n)) instead of X_n alone (ablation)Deep Optimal Stopping · Max-call optionsefficiencyImproved
apply the method to high dimension d=500 symmetric max-callDeep Optimal Stopping · Symmetric max-call optioncomputation time t_L: 28.7 -> 493.4Improved
compare with binomial lattice pricesDeep Optimal Stopping · Symmetric max-call, d=2, s0=100price: 13.899 vs 13.902No clear effect
use the callable feature versus non-callable MBRCMulti barrier reverse convertible · MBRC d=30, rho=0.1fair value: 99.279 -> 72.393Improved
increase number of underlying assets from 2 to 30 (rho=0.1)Callable MBRC · MBRCfair value: 97.634 -> 72.393Hurt
double J for the dual bound near H=1/2 (ablation)Deep Optimal Stopping · Fractional Brownian motionupper bound time: 17,000 -> 34,000 secondsMixed
compare against heuristic stopping rules for fBM, H in (1/2,1)Deep Optimal Stopping · Fractional Brownian motionexpected payoff: up to three times higherImproved
compare against heuristic stopping rules for fBM, H in (0,1/2)Deep Optimal Stopping · Fractional Brownian motionexpected payoff: up to five times higherImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy