Greedy Selection under Independent Increments: A Toy Model Analysis
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916805722767360 |
|---|---|
| author | Yang, Huitao |
| author_facet | Yang, Huitao |
| contents | We study an iterative selection problem over N i.i.d. discrete-time stochastic processes with independent increments. At each stage, a fixed number of processes are retained based on their observed values. Under this simple model, we prove that the optimal strategy for selecting the final maximum-value process is to apply greedy selection at each stage. While the result relies on strong independence assumptions, it offers a clean justification for greedy heuristics in multi-stage elimination settings and may serve as a toy example for understanding related algorithms in high-dimensional applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17941 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Greedy Selection under Independent Increments: A Toy Model Analysis Yang, Huitao Probability Artificial Intelligence Machine Learning We study an iterative selection problem over N i.i.d. discrete-time stochastic processes with independent increments. At each stage, a fixed number of processes are retained based on their observed values. Under this simple model, we prove that the optimal strategy for selecting the final maximum-value process is to apply greedy selection at each stage. While the result relies on strong independence assumptions, it offers a clean justification for greedy heuristics in multi-stage elimination settings and may serve as a toy example for understanding related algorithms in high-dimensional applications. |
| title | Greedy Selection under Independent Increments: A Toy Model Analysis |
| topic | Probability Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2506.17941 |