Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2405.02726 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911866843824128 |
|---|---|
| author | Veprikov, Andrey Afanasiev, Alexander Khritankov, Anton |
| author_facet | Veprikov, Andrey Afanasiev, Alexander Khritankov, Anton |
| contents | Widespread deployment of societal-scale machine learning systems necessitates a thorough understanding of the resulting long-term effects these systems have on their environment, including loss of trustworthiness, bias amplification, and violation of AI safety requirements. We introduce a repeated learning process to jointly describe several phenomena attributed to unintended hidden feedback loops, such as error amplification, induced concept drift, echo chambers and others. The process comprises the entire cycle of obtaining the data, training the predictive model, and delivering predictions to end-users within a single mathematical model. A distinctive feature of such repeated learning setting is that the state of the environment becomes causally dependent on the learner itself over time, thus violating the usual assumptions about the data distribution. We present a novel dynamical systems model of the repeated learning process and prove the limiting set of probability distributions for positive and negative feedback loop modes of the system operation. We conduct a series of computational experiments using an exemplary supervised learning problem on two synthetic data sets. The results of the experiments correspond to the theoretical predictions derived from the dynamical model. Our results demonstrate the feasibility of the proposed approach for studying the repeated learning processes in machine learning systems and open a range of opportunities for further research in the area. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02726 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Mathematical Model of the Hidden Feedback Loop Effect in Machine Learning Systems Veprikov, Andrey Afanasiev, Alexander Khritankov, Anton Machine Learning Systems and Control Widespread deployment of societal-scale machine learning systems necessitates a thorough understanding of the resulting long-term effects these systems have on their environment, including loss of trustworthiness, bias amplification, and violation of AI safety requirements. We introduce a repeated learning process to jointly describe several phenomena attributed to unintended hidden feedback loops, such as error amplification, induced concept drift, echo chambers and others. The process comprises the entire cycle of obtaining the data, training the predictive model, and delivering predictions to end-users within a single mathematical model. A distinctive feature of such repeated learning setting is that the state of the environment becomes causally dependent on the learner itself over time, thus violating the usual assumptions about the data distribution. We present a novel dynamical systems model of the repeated learning process and prove the limiting set of probability distributions for positive and negative feedback loop modes of the system operation. We conduct a series of computational experiments using an exemplary supervised learning problem on two synthetic data sets. The results of the experiments correspond to the theoretical predictions derived from the dynamical model. Our results demonstrate the feasibility of the proposed approach for studying the repeated learning processes in machine learning systems and open a range of opportunities for further research in the area. |
| title | A Mathematical Model of the Hidden Feedback Loop Effect in Machine Learning Systems |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2405.02726 |