Understanding Fixed Predictions via Confined Regions
Machine learning models are designed to predict outcomes using features about an individual, but fail to take into account how individuals can change them. Consequently, models can assign fixed predictions that deny individuals recourse to change their outcome. This work develops a new paradigm to identify fixed predictions by finding confined regions in which all individuals receive fixed predictions. We introduce the first method, ReVer, for this task, using tools from mixed-integer quadratically constrained programming. Our approach certifies recourse for out-of-sample data, provides interpretable descriptions of confined regions, and runs in seconds on real world datasets. We conduct a comprehensive empirical study of confined regions across diverse applications. Our results highlight that existing point-wise verification methods fail to discover confined regions, while ReVer provably succeeds.
Code (1)
Similar Papers 제목 키워드 기반
OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models
Understanding human-to-human interactions, especially in contexts like public security surveillance, is critical for monitoring and maintaining safety. Traditional activity recognition systems are limited by fixed vocabu…
Activity RecognitionHuman Interaction RecognitionVideo UnderstandingVGR: Visual Grounded Reasoning
In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or scie…
Large Language ModelMathMultimodal Large Language ModelVisual ReasoningAdaptive Object Detection Using Adjacency and Zoom Prediction
State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are comput…
Objectobject-detectionObject DetectionPredictionPredicting Confinement Effect of Carbon Fiber Reinforced Polymers on Strength of Concrete using Metaheuristics-based Artificial Neural Networks
This article deals with the study of predicting the confinement effect of carbon fiber reinforced polymers (CFRPs) on concrete cylinder strength using metaheuristics-based artificial neural networks. A detailed database …
MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding
Large Vision-Language Models (LVLMs) have achieved remarkable performance in many vision-language tasks, yet their capabilities in fine-grained visual understanding remain insufficiently evaluated. Existing benchmarks ei…
Benchmarkingdocument understandingOptical Character Recognition (OCR)