212 reads

Theoretical Derivations: Cross-Entropy Loss and Energy Functions in LLMs

by reinforcem...June 24th, 2025
Read on Terminal Reader
Read this story w/o Javascript
tldt arrow

Too Long; Didn't Read

Explore rigorous mathematical proofs, including properties of incomplete gamma functions, Stirling's approximation, and derivations of loss functions and partition functions for our theoretical model.

People Mentioned

Mention Thumbnail

Companies Mentioned

Mention Thumbnail
Mention Thumbnail
featured image - Theoretical Derivations: Cross-Entropy Loss and Energy Functions in LLMs
Reinforcement Technology Advancements HackerNoon profile picture
0-item

Abstract and 1 Introduction

2 Related Work

3 Model and 3.1 Associative memories

3.2 Transformer blocks

4 A New Energy Function

4.1 The layered structure

5 Cross-Entropy Loss

6 Empirical Results and 6.1 Empirical evaluation of the radius

6.2 Training GPT-2

6.3 Training Vanilla Transformers

7 Conclusion and Acknowledgments


Appendix A. Deferred Tables

Appendix B. Some Properties of the Energy Functions

Appendix C. Deferred Proofs from Section 5

Appendix D. Transformer Details: Using GPT-2 as an Example


References

Appendix C. Deferred Proofs from Section 5

C.1 Proof of Proposition 4

C.2


Authors:

(1) Xueyan Niu, Theory Laboratory, Central Research Institute, 2012 Laboratories, Huawei Technologies Co., Ltd.;

(2) Bo Bai baibo (8@huawei.com);

(3) Lei Deng (deng.lei2@huawei.com);

(4) Wei Han (harvey.hanwei@huawei.com).


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


Trending Topics

blockchaincryptocurrencyhackernoon-top-storyprogrammingsoftware-developmenttechnologystartuphackernoon-booksBitcoinbooks