Papers › From system models to class models: An in-context learning paradigm

From system models to class models: An in-context learning paradigm

25 Aug 2023arXiv:2308.13380archive 2025-07-28

Marco Forgione, Filippo Pura, Dario Piga

Is it possible to understand the intricacies of a dynamical system not solely from its input/output pattern, but also by observing the behavior of other systems within the same class? This central question drives the study presented in this paper. In response to this query, we introduce a novel paradigm for system identification, addressing two primary tasks: one-step-ahead prediction and multi-step simulation. Unlike conventional methods, we do not directly estimate a model for the specific system. Instead, we learn a meta model that represents a class of dynamical systems. This meta model is trained on a potentially infinite stream of synthetic data, generated by simulators whose settings are randomly extracted from a probability distribution. When provided with a context from a new system-specifically, an input/output sequence-the meta model implicitly discerns its dynamics, enabling predictions of its behavior. The proposed approach harnesses the power of Transformers, renowned for their \emph{in-context learning} capabilities. For one-step prediction, a GPT-like decoder-only architecture is utilized, whereas the simulation problem employs an encoder-decoder structure. Initial experimental results affirmatively answer our foundational question, opening doors to fresh research avenues in system identification.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

forgi86/sysid-neural-transformers officialmentioned in papermentioned on GitHubpytorch report
forgi86/sysid-transformers officialmentioned in papermentioned on GitHubpytorch report
buswayne/sysid-transformers-control mentioned on GitHubpytorch report
forgi86/lru-reduction mentioned on GitHubjax report
forgi86/sysid-transformers-transfer mentioned on GitHubpytorch report
mattrufolo/sysid-prob-transformer mentioned on GitHubpytorch report
mattrufolo/sysid-robust-transformer mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderIn-Context Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections