6 citations · 9 across the 12 of their papers we have counts for
13 papers
Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift
Salim I. Amoukou, Emanuele Albini, Tom Bewley +2
We propose a unified framework for addressing three key challenges of distribution shift: (1) estimating a model's performance on an unlabeled target domain, (2) explaining the shi…
Correcting Split Selection in Online Decision Trees via Anytime-Valid Inference
Salim I. Amoukou, Saumitra Mishra, Manuela Veloso
Bagging-based ensembles, most notably Adaptive Random Forests, are among the strongest performers for learning from data streams. A common denominator across these methods is their…
Regional Explanations: Bridging Local and Global Variable Importance
Salim I. Amoukou, Nicolas J-B. Brunel
We analyze two widely used local attribution methods, Local Shapley Values and LIME, which aim to quantify the contribution of a feature value to a specific prediction $f(x_1…
ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values
Tom Bewley, Salim I. Amoukou, Emanuele Albini +2
Changes in input distribution can induce shifts in the average predictions of machine learning models. Such prediction shifts may impact downstream business outcomes (e.g. a bank's…
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
Anna Hedström, Salim I. Amoukou, Tom Bewley +2
We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventi…
Representation Consistency for Accurate and Coherent LLM Answer Aggregation
Junqi Jiang, Tom Bewley, Salim I. Amoukou +4
Test-time scaling improves large language models' (LLMs) performance by allocating more compute budget during inference. To achieve this, existing methods often require intricate m…
Sequential Harmful Shift Detection Without Labels
Salim I. Amoukou, Tom Bewley, Saumitra Mishra +3
We introduce a novel approach for detecting distribution shifts that negatively impact the performance of machine learning models in continuous production environments, which requi…
Counterfactual Metarules for Local and Global Recourse
Tom Bewley, Salim I. Amoukou, Saumitra Mishra +2
We introduce T-CREx, a novel model-agnostic method for local and global counterfactual explanation (CE), which summarises recourse options for both individuals and groups in the fo…
Adaptive Conformal Prediction by Reweighting Nonconformity Score
Salim I. Amoukou, Nicolas J. B Brunel
Despite attractive theoretical guarantees and practical successes, Predictive Interval (PI) given by Conformal Prediction (CP) may not reflect the uncertainty of a given model. Thi…
Local and Regional Counterfactual Rules: Summarized and Robust Recourses
Salim I. Amoukou, Nicolas J. B Brunel
Counterfactual Explanations (CE) face several unresolved challenges, such as ensuring stability, synthesizing multiple CEs, and providing plausibility and sparsity guarantees. From…
Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models
Salim I. Amoukou, Nicolas J. B Brunel
To explain the decision of any model, we extend the notion of probabilistic Sufficient Explanations (P-SE). For each instance, this approach selects the minimal subset of features…
Accurate Shapley Values for explaining tree-based models
Salim I. Amoukou, Nicolas J-B. Brunel, Tangi Salaün
Shapley Values (SV) are widely used in explainable AI, but their estimation and interpretation can be challenging, leading to inaccurate inferences and explanations. As a starting…
The Shapley Value of coalition of variables provides better explanations
Salim I. Amoukou, Nicolas J-B. Brunel, Tangi Salaün
While Shapley Values (SV) are one of the gold standard for interpreting machine learning models, we show that they are still poorly understood, in particular in the presence of cat…