SimPO: Simultaneous Prediction and Optimization
Many machine learning (ML) models are integrated within the context of a larger system as part of a key component for decision making processes. Concretely, predictive models are often employed in estimating the parameters for the input values that are utilized for optimization models as isolated processes. Traditionally, the predictive models are built first, then the model outputs are used to generate decision values separately. However, it is often the case that the prediction values that are trained independently of the optimization process produce sub-optimal solutions. In this paper, we propose a formulation for the Simultaneous Prediction and Optimization (SimPO) framework. This framework introduces the use of a joint weighted loss of a decision-driven predictive ML model and an optimization objective function, which is optimized end-to-end directly through gradient-based methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingPredictionSimilar Papers 제목 키워드 기반
SimPO: Simple Preference Optimization with a Reference-Free Reward
Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that reparameterizes reward functions in reinforcement learning from human feedback (RLHF) to enhance simplicity and trainin…
ChatbotInstruction Following$ξ$-DPO: Direct Preference Optimization via Ratio Reward Margin
Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(SimPO) demonstrating strong performance by eliminating the…
Reinforcement LearningRePO: ReLU-based Preference Optimization
Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm wi…
Failure Modes of Maximum Entropy RLHF
In this paper, we show that Simple Preference Optimization (SimPO) can be derived as Maximum Entropy Reinforcement Learning, providing a theoretical foundation for this reference-free method. Motivated by SimPO's strong …
Reinforcement Learning$α$-DPO: Adaptive Reward Margin is What Direct Preference Optimization Needs
Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment,…
Computational Efficiency