Deriving the Optimum of the KL-Constrained Reward Maximization Objective

The mathematical derivations in this appendix aim to derive Equation 4, which represents the objective function for optimizing the policy in the KL-constrained reward maximization problem. The objective is to find a policy that aligns well with human preferences while minimizing the KL-divergence from a reference policy. The partition function Z(x’, π) plays a crucial role in normalizing the probability distribution.


This content originally appeared on HackerNoon and was authored by Writings, Papers and Blogs on Text Models

:::info Authors:

(1) Rafael Rafailo, Stanford University and Equal contribution; more junior authors listed earlier;

(2) Archit Sharma, Stanford University and Equal contribution; more junior authors listed earlier;

(3) Eric Mitchel, Stanford University and Equal contribution; more junior authors listed earlier;

(4) Stefano Ermon, CZ Biohub;

(5) Christopher D. Manning, Stanford University;

(6) Chelsea Finn, Stanford University.

:::

Abstract and 1. Introduction

2 Related Work

3 Preliminaries

4 Direct Preference Optimization

5 Theoretical Analysis of DPO

6 Experiments

7 Discussion, Acknowledgements, and References

Author Contributions

\ A Mathematical Derivations

A.1 Deriving the Optimum of the KL-Constrained Reward Maximization Objective

A.2 Deriving the DPO Objective Under the Bradley-Terry Model

A.3 Deriving the DPO Objective Under the Plackett-Luce Model

A.4 Deriving the Gradient of the DPO Objective and A.5 Proof of Lemma 1 and 2

A.6 Proof of Theorem 1

\ B DPO Implementation Details and Hyperparameters

\ C Further Details on the Experimental Set-Up and C.1 IMDb Sentiment Experiment and Baseline Details

C.2 GPT-4 prompts for computing summarization and dialogue win rates

C.3 Unlikelihood baseline

\ D Additional Empirical Results

D.1 Performance of Best of N baseline for Various N and D.2 Sample Responses and GPT-4 Judgments

D.3 Human study details

Mathematical Derivations

A.1 Deriving the Optimum of the KL-Constrained Reward Maximization Objective

In this appendix, we will derive Eq. 4. Analogously to Eq. 3, we optimize the following objective:

\

\ where we have partition function:

\

\

\

:::info This paper is available on arxiv under CC BY-NC-ND 4.0 DEED license.

:::

\


This content originally appeared on HackerNoon and was authored by Writings, Papers and Blogs on Text Models


Print Share Comment Cite Upload Translate Updates
APA

Writings, Papers and Blogs on Text Models | Sciencx (2024-08-25T21:13:38+00:00) Deriving the Optimum of the KL-Constrained Reward Maximization Objective. Retrieved from https://www.scien.cx/2024/08/25/deriving-the-optimum-of-the-kl-constrained-reward-maximization-objective/

MLA
" » Deriving the Optimum of the KL-Constrained Reward Maximization Objective." Writings, Papers and Blogs on Text Models | Sciencx - Sunday August 25, 2024, https://www.scien.cx/2024/08/25/deriving-the-optimum-of-the-kl-constrained-reward-maximization-objective/
HARVARD
Writings, Papers and Blogs on Text Models | Sciencx Sunday August 25, 2024 » Deriving the Optimum of the KL-Constrained Reward Maximization Objective., viewed ,<https://www.scien.cx/2024/08/25/deriving-the-optimum-of-the-kl-constrained-reward-maximization-objective/>
VANCOUVER
Writings, Papers and Blogs on Text Models | Sciencx - » Deriving the Optimum of the KL-Constrained Reward Maximization Objective. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2024/08/25/deriving-the-optimum-of-the-kl-constrained-reward-maximization-objective/
CHICAGO
" » Deriving the Optimum of the KL-Constrained Reward Maximization Objective." Writings, Papers and Blogs on Text Models | Sciencx - Accessed . https://www.scien.cx/2024/08/25/deriving-the-optimum-of-the-kl-constrained-reward-maximization-objective/
IEEE
" » Deriving the Optimum of the KL-Constrained Reward Maximization Objective." Writings, Papers and Blogs on Text Models | Sciencx [Online]. Available: https://www.scien.cx/2024/08/25/deriving-the-optimum-of-the-kl-constrained-reward-maximization-objective/. [Accessed: ]
rf:citation
» Deriving the Optimum of the KL-Constrained Reward Maximization Objective | Writings, Papers and Blogs on Text Models | Sciencx | https://www.scien.cx/2024/08/25/deriving-the-optimum-of-the-kl-constrained-reward-maximization-objective/ |

Please log in to upload a file.




There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.