From 5fbdafe05e6c97e93520720edc95e4b7d40d6a79 Mon Sep 17 00:00:00 2001 From: Daniele Lotito Date: Thu, 26 Feb 2026 11:14:31 +0000 Subject: [PATCH 1/8] docs: add TRIM readme --- plugins/operators/trim/README.md | 59 ++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/plugins/operators/trim/README.md b/plugins/operators/trim/README.md index e69de29bb..bce6e298a 100644 --- a/plugins/operators/trim/README.md +++ b/plugins/operators/trim/README.md @@ -0,0 +1,59 @@ +# ADO TRIM Operator + +`ado-trim` is an operator plugin for the +[Accelerated Discovery Orchestrator (ADO)](https://github.com/IBM/ado), +providing the Transfer Refined Iterative Modeling (TRIM) characterization +operator. + +**TRIM (Transfer Refined Iterative Modeling)** is designed to efficiently build +a surrogate model of a complex system. It is ideal for scenarios where exploring +a parameter space is time-consuming or expensive. TRIM intelligently samples +just enough points to create a stable and accurate predictive model, saving +significant time and resources. + +## How it Works + +The `TRIM` operator works in two main phases: + +1. **No-Priors Characterization**: If the system has not been measured before, + TRIM starts by sampling a small, representative set of points using a + space-filling algorithm to get a baseline understanding of the parameter + space. + +2. **Iterative Modeling**: +3. This phase begins by using all currently available data to train a single + preliminary AutoGluon model. The feature importance from this model is used + to order for all remaining unmeasured points. TRIM then enters a loop where + it: + + - Samples the next point and adds it to the dataset. + - Trains a model on the gathered data using `AutoGluon`. + - Evaluates the expected improvement of a model trained on a larger dataset + by comparing the new model's performance against that of previous models. + +This loop continues until the improvement is below a threshold, at which point +TRIM automatically stops. Finally, it trains one high-quality model on all +collected data and saves it for your use. It also outputs a file containing the +measured values and predictions for all points in your space. + +## Installation + +You can install the `TRIM` operator directly from PyPI: + +```bash +pip install ado-trim +``` + +This will install the operator and its dependencies, including `ado-core`. Are +you looking forward to use TRIM? Check the +[quick start guide](https://ibm.github.io/ado/examples/trim/). + +## More Information + +For detailed documentation, configuration guides, and more examples, please +visit the official ADO website: + +- **TRIM Example**: + [https://ibm.github.io/ado/examples/trim/](https://ibm.github.io/ado/examples/trim/) +- **ADO Operators**: + [https://ibm.github.io/ado/operators/explore_operators/](https://ibm.github.io/ado/operators/explore_operators/) From 60c40200c8d488d04c1f172bc49944e9dfc1753e Mon Sep 17 00:00:00 2001 From: Daniele Lotito Date: Thu, 26 Feb 2026 11:30:27 +0000 Subject: [PATCH 2/8] docs: remove repetition --- plugins/operators/trim/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/plugins/operators/trim/README.md b/plugins/operators/trim/README.md index bce6e298a..3c62496fe 100644 --- a/plugins/operators/trim/README.md +++ b/plugins/operators/trim/README.md @@ -5,7 +5,7 @@ providing the Transfer Refined Iterative Modeling (TRIM) characterization operator. -**TRIM (Transfer Refined Iterative Modeling)** is designed to efficiently build +**TRIM** is designed to efficiently build a surrogate model of a complex system. It is ideal for scenarios where exploring a parameter space is time-consuming or expensive. TRIM intelligently samples just enough points to create a stable and accurate predictive model, saving From 0556b21283d0a2427c63d21581d51a88c6021455 Mon Sep 17 00:00:00 2001 From: Daniele Lotito <99284466+danielelotito@users.noreply.github.com> Date: Thu, 26 Feb 2026 13:34:17 +0000 Subject: [PATCH 3/8] Update plugins/operators/trim/README.md Co-authored-by: Alessandro Pomponio <10339005+AlessandroPomponio@users.noreply.github.com> Signed-off-by: Daniele Lotito <99284466+danielelotito@users.noreply.github.com> --- plugins/operators/trim/README.md | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/plugins/operators/trim/README.md b/plugins/operators/trim/README.md index 3c62496fe..27cea6e64 100644 --- a/plugins/operators/trim/README.md +++ b/plugins/operators/trim/README.md @@ -20,16 +20,15 @@ The `TRIM` operator works in two main phases: space-filling algorithm to get a baseline understanding of the parameter space. -2. **Iterative Modeling**: -3. This phase begins by using all currently available data to train a single - preliminary AutoGluon model. The feature importance from this model is used - to order for all remaining unmeasured points. TRIM then enters a loop where - it: - - - Samples the next point and adds it to the dataset. - - Trains a model on the gathered data using `AutoGluon`. - - Evaluates the expected improvement of a model trained on a larger dataset - by comparing the new model's performance against that of previous models. +2. **Iterative Modeling**: This phase begins by using all currently available + data to train a single preliminary AutoGluon model. The feature importance + from this model is used to order for all remaining unmeasured points. TRIM + then enters a loop where it: + + - Samples the next point and adds it to the dataset. + - Trains a model on the gathered data using `AutoGluon`. + - Evaluates the expected improvement of a model trained on a larger dataset + by comparing the new model's performance against that of previous models. This loop continues until the improvement is below a threshold, at which point TRIM automatically stops. Finally, it trains one high-quality model on all From 4a31f46ad39653415422c3c56afc97c30d0a377c Mon Sep 17 00:00:00 2001 From: Daniele Lotito <99284466+danielelotito@users.noreply.github.com> Date: Thu, 26 Feb 2026 13:34:36 +0000 Subject: [PATCH 4/8] Update plugins/operators/trim/README.md Co-authored-by: Alessandro Pomponio <10339005+AlessandroPomponio@users.noreply.github.com> Signed-off-by: Daniele Lotito <99284466+danielelotito@users.noreply.github.com> --- plugins/operators/trim/README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/plugins/operators/trim/README.md b/plugins/operators/trim/README.md index 27cea6e64..5664ef918 100644 --- a/plugins/operators/trim/README.md +++ b/plugins/operators/trim/README.md @@ -37,7 +37,8 @@ measured values and predictions for all points in your space. ## Installation -You can install the `TRIM` operator directly from PyPI: +You can install the `TRIM` operator and its dependencies (including `ado-core`) +directly from PyPI: ```bash pip install ado-trim From e8a3b1ae7b1ed2c2d77dd0ee04cb3d8f2f020398 Mon Sep 17 00:00:00 2001 From: Daniele Lotito <99284466+danielelotito@users.noreply.github.com> Date: Thu, 26 Feb 2026 13:35:01 +0000 Subject: [PATCH 5/8] Update plugins/operators/trim/README.md Co-authored-by: Alessandro Pomponio <10339005+AlessandroPomponio@users.noreply.github.com> Signed-off-by: Daniele Lotito <99284466+danielelotito@users.noreply.github.com> --- plugins/operators/trim/README.md | 4 ---- 1 file changed, 4 deletions(-) diff --git a/plugins/operators/trim/README.md b/plugins/operators/trim/README.md index 5664ef918..d49a74da3 100644 --- a/plugins/operators/trim/README.md +++ b/plugins/operators/trim/README.md @@ -44,10 +44,6 @@ directly from PyPI: pip install ado-trim ``` -This will install the operator and its dependencies, including `ado-core`. Are -you looking forward to use TRIM? Check the -[quick start guide](https://ibm.github.io/ado/examples/trim/). - ## More Information For detailed documentation, configuration guides, and more examples, please From 27c8ccf30ab67b94c878074e212b8376bc105f36 Mon Sep 17 00:00:00 2001 From: Daniele Lotito <99284466+danielelotito@users.noreply.github.com> Date: Thu, 26 Feb 2026 13:35:19 +0000 Subject: [PATCH 6/8] Update plugins/operators/trim/README.md Co-authored-by: Alessandro Pomponio <10339005+AlessandroPomponio@users.noreply.github.com> Signed-off-by: Daniele Lotito <99284466+danielelotito@users.noreply.github.com> --- plugins/operators/trim/README.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/plugins/operators/trim/README.md b/plugins/operators/trim/README.md index d49a74da3..37bc4ea0c 100644 --- a/plugins/operators/trim/README.md +++ b/plugins/operators/trim/README.md @@ -46,10 +46,10 @@ pip install ado-trim ## More Information -For detailed documentation, configuration guides, and more examples, please -visit the official ADO website: +To learn more about TRIM and explore the full capabilities of ADO, including +detailed documentation, configuration guides, and additional examples, visit the +official ADO website: -- **TRIM Example**: - [https://ibm.github.io/ado/examples/trim/](https://ibm.github.io/ado/examples/trim/) -- **ADO Operators**: - [https://ibm.github.io/ado/operators/explore_operators/](https://ibm.github.io/ado/operators/explore_operators/) +- **TRIM Quickstart**: +- **Configuring TRIM**: +- **ADO Documentation**: From 5724446062d32ca852dba0da743360899a2f5820 Mon Sep 17 00:00:00 2001 From: Daniele Lotito Date: Thu, 26 Feb 2026 13:38:21 +0000 Subject: [PATCH 7/8] docs: remove reference to autogluon --- plugins/operators/trim/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/plugins/operators/trim/README.md b/plugins/operators/trim/README.md index 37bc4ea0c..30f3c4bc2 100644 --- a/plugins/operators/trim/README.md +++ b/plugins/operators/trim/README.md @@ -21,12 +21,12 @@ The `TRIM` operator works in two main phases: space. 2. **Iterative Modeling**: This phase begins by using all currently available - data to train a single preliminary AutoGluon model. The feature importance + data to train a single preliminary surrogate model. The feature importance from this model is used to order for all remaining unmeasured points. TRIM then enters a loop where it: - Samples the next point and adds it to the dataset. - - Trains a model on the gathered data using `AutoGluon`. + - Trains a model on the gathered data. - Evaluates the expected improvement of a model trained on a larger dataset by comparing the new model's performance against that of previous models. From 395ea54252ae911b76c62adcc6605e12c0dc87f6 Mon Sep 17 00:00:00 2001 From: Daniele Lotito Date: Thu, 26 Feb 2026 13:41:18 +0000 Subject: [PATCH 8/8] docs(pretty): format with pretty --- plugins/operators/trim/README.md | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/plugins/operators/trim/README.md b/plugins/operators/trim/README.md index 30f3c4bc2..d5ff35d08 100644 --- a/plugins/operators/trim/README.md +++ b/plugins/operators/trim/README.md @@ -5,26 +5,24 @@ providing the Transfer Refined Iterative Modeling (TRIM) characterization operator. -**TRIM** is designed to efficiently build -a surrogate model of a complex system. It is ideal for scenarios where exploring -a parameter space is time-consuming or expensive. TRIM intelligently samples -just enough points to create a stable and accurate predictive model, saving -significant time and resources. +**TRIM** is designed to efficiently build a surrogate model of a complex system. +It is ideal for scenarios where exploring a parameter space is time-consuming or +expensive. TRIM intelligently samples just enough points to create a stable and +accurate predictive model, saving significant time and resources. ## How it Works The `TRIM` operator works in two main phases: 1. **No-Priors Characterization**: If the system has not been measured before, - TRIM starts by sampling a small, representative set of points using a - space-filling algorithm to get a baseline understanding of the parameter - space. + TRIM starts by sampling a small, representative set of points using a + space-filling algorithm to get a baseline understanding of the parameter + space. 2. **Iterative Modeling**: This phase begins by using all currently available data to train a single preliminary surrogate model. The feature importance from this model is used to order for all remaining unmeasured points. TRIM then enters a loop where it: - - Samples the next point and adds it to the dataset. - Trains a model on the gathered data. - Evaluates the expected improvement of a model trained on a larger dataset