# On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning

arXiv: https://arxiv.org/abs/1704.00805 · HTML: https://mlsanity.com/paper/1704.00805/

## Key facts

- Cited by 142 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2017.

## Built on by (most cited first, 30 of 142)

- [cosFormer: Rethinking Softmax in Attention](https://mlsanity.com/paper/2202.08791/) (2022)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Structure-Aware Transformer for Graph Representation Learning](https://mlsanity.com/paper/2202.03036/) (2022)
- [The Devil in Linear Transformer](https://mlsanity.com/paper/2210.10340/) (2022)
- [Voice2Series: Reprogramming Acoustic Models for Time Series Classification](https://mlsanity.com/paper/2106.09296/) (2021)
- [CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP](https://mlsanity.com/paper/2110.11316/) (2021)
- [Statistical Foundations of Prior-Data Fitted Networks](https://mlsanity.com/paper/2305.11097/) (2023)
- [Tighter expected generalization error bounds via Wasserstein distance](https://mlsanity.com/paper/2101.09315/) (2021)
- [On Sparse Modern Hopfield Model](https://mlsanity.com/paper/2309.12673/) (2023)
- [Do LLM Agents Have Regret? A Case Study in Online Learning and Games](https://mlsanity.com/paper/2403.16843/) (2024)
- [Towards Consistent Video Editing with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.17431/) (2023)
- [Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning](https://mlsanity.com/paper/2309.05911/) (2023)
- [Attention Is All You Need for KV Cache in Diffusion LLMs](https://mlsanity.com/paper/2510.14973/) (2025)
- [Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning](https://mlsanity.com/paper/2401.15273/) (2024)
- [Integrated Conditional Estimation-Optimization](https://mlsanity.com/paper/2110.12351/) (2021)
- [REFINE: Inversion-Free Backdoor Defense via Model Reprogramming](https://mlsanity.com/paper/2502.18508/) (2025)
- [Softmax is 1/2-Lipschitz: A tight bound across all ℓp norms](https://mlsanity.com/paper/2510.23012/) (2025)
- [Transformer Uncertainty Estimation with Hierarchical Stochastic Attention](https://mlsanity.com/paper/2112.13776/) (2021)
- [Replicability in Reinforcement Learning](https://mlsanity.com/paper/2305.19562/) (2023)
- [Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path](https://mlsanity.com/paper/2208.11639/) (2022)
- [Distill n' Explain: explaining graph neural networks using simple surrogates](https://mlsanity.com/paper/2303.10139/) (2023)
- [With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning](https://mlsanity.com/paper/2308.12383/) (2023)
- [Neural Architecture Search on Efficient Transformers and Beyond](https://mlsanity.com/paper/2207.13955/) (2022)
- [Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimation](https://mlsanity.com/paper/2303.13429/) (2023)
- [Beyond Adult and COMPAS: Fairness in Multi-Class Prediction](https://mlsanity.com/paper/2206.07801/) (2022)
- [Statistical Advantages of Perturbing Cosine Router in Mixture of Experts](https://mlsanity.com/paper/2405.14131/) (2024)
- [Lambda-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells](https://mlsanity.com/paper/2210.07998/) (2022)
- [A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games](https://mlsanity.com/paper/2303.03100/) (2023)
- [Explainable AI via Learning to Optimize](https://mlsanity.com/paper/2204.14174/) (2022)
- [The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images](https://mlsanity.com/paper/2401.08865/) (2024)

## Abstract (arXiv)

In this paper, we utilize results from convex analysis and monotone operator theory to derive additional properties of the softmax function that have not yet been covered in the existing literature. In particular, we show that the softmax function is the monotone gradient map of the log-sum-exp function. By exploiting this connection, we show that the inverse temperature parameter determines the Lipschitz and co-coercivity properties of the softmax function. We then demonstrate the usefulness of these properties through an application in game-theoretic reinforcement learning.