Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees
We consider the task of training machine learning models with data-dependent constraints. Such constraints often arise as empirical versions of expected value constraints that enforce fairness or stability goals. We reformulate data-dependent constraints so that they are calibrated: enforcing the reformulated constraints guarantees that their expected value counterparts are satisfied with a user-prescribed probability. The resulting optimization problem is amendable to standard stochastic optimization algorithms, and we demonstrate the efficacy of our method on a fairness-sensitive classification task where we wish to guarantee the classifier's fairness (at test time).
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessStochastic OptimizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches. At the same time, these problems are often accompanied by rich domain …
Impulsive Relative Motion Control with Continuous-Time Constraint Satisfaction for Cislunar Space Missions
Recent investments in cislunar applications open new frontiers for space missions within highly nonlinear dynamical regimes. In this paper, we propose a method based on Sequential Convex Programming (SCP) to loiter aroun…
CPUAn inexact-penalty method for GNE seeking in games with dynamic agents
We consider a network of autonomous agents whose outputs are actions in a game with coupled constraints. In such network scenarios, agents seeking to minimize coupled cost functions using distributed information while sa…
DIALEVAL: Automated Type-Theoretic Evaluation of LLM Instruction Following
Evaluating instruction following in Large Language Models requires decomposing instructions into verifiable requirements and assessing satisfaction--tasks currently dependent on manual annotation and uniform criteria tha…
Instruction FollowingProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control
Generating human motion with precise spatial control is a challenging problem. Existing approaches often require task-specific training or slow optimization, and enforcing hard constraints frequently disrupts motion natu…