paper-with-me

홈 › Papers

Synthesizing Pareto-Optimal Interpretations for Black-Box Models

2021-08-16 · Hazem Torfah, Shetal Shah, Supratik Chakraborty, S. Akshay, Sanjit A. Seshia

We present a new multi-objective optimization approach for synthesizing interpretations that "explain" the behavior of black-box machine learning models. Constructing human-understandable interpretations for black-box models often requires balancing conflicting objectives. A simple interpretation may be easier to understand for humans while being less precise in its predictions vis-a-vis a complex interpretation. Existing methods for synthesizing interpretations use a single objective function and are often optimized for a single class of interpretations. In contrast, we provide a more general and multi-objective synthesis framework that allows users to choose (1) the class of syntactic templates from which an interpretation should be synthesized, and (2) quantitative measures on both the correctness and explainability of an interpretation. For a given black-box, our approach yields a set of Pareto-optimal interpretations with respect to the correctness and explainability measures. We show that the underlying multi-objective optimization problem can be solved via a reduction to quantitative constraint solving, such as weighted maximum satisfiability. To demonstrate the benefits of our approach, we have applied it to synthesize interpretations for black-box neural-network classifiers. Our experiments show that there often exists a rich and varied set of choices for interpretations that are missed by existing approaches.

📄 PDF Abstract BibTeX arXiv:2108.07307

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Locally Pareto-Optimal Interpretations for Black-Box Machine Learning Models

2025-08-21 · Aniruddha Joshi, Supratik Chakraborty, S Akshay, Shetal Shah 외 arxiv

Creating meaningful interpretations for black-box machine learning models involves balancing two often conflicting objectives: accuracy and explainability. Exploring the trade-off between these objectives is essential fo…

syftr: Pareto-Optimal Generative AI

2025-05-26 · Alexander Conway, Debadeepta Dey, Stefan Hackmann, Matthew Hausknecht 외

Retrieval-Augmented Generation (RAG) pipelines are central to applying large language models (LLMs) to proprietary or dynamic data. However, building effective RAG flows is complex, requiring careful selection among vect…

Bayesian OptimizationRAGRetrieval-augmented Generation

Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations

2024-01-25 · Xinyue Xu, Yi Qin, Lu Mi, Hao Wang 외

Existing methods, such as concept bottleneck models (CBMs), have been successful in providing concept-based interpretations for black-box deep learning models. They typically work by predicting concepts given the input a…

Neural Solvers for Fast and Accurate Numerical Optimal Control

2022-03-13 · NeurIPS Workshop DLDE 2021 12 · Federico Berto, Stefano Massaroli, Michael Poli, Jinkyoo Park

Synthesizing optimal controllers for dynamical systems often involves solving optimization problems with hard real-time constraints. These constraints determine the class of numerical methods that can be applied: computa…

An Interpretable Probabilistic Approach for Demystifying Black-box Predictive Models

2020-07-21 · Catarina Moreira, Yu-Liang Chou, Mythreyi Velmurugan, Chun Ouyang 외

The use of sophisticated machine learning models for critical decision making is faced with a challenge that these models are often applied as a "black-box". This has led to an increased interest in interpretable machine…

BIG-bench Machine LearningDecision MakingInterpretable Machine LearningPrediction