Computable Fairness: Boltzmann-Softmax Control for AI Resource Allocation

2026-04-12 · Ji-Won Park, Chae Un Kim arxiv

In large-scale AI systems, allocating scarce resources such as GPU compute time and bandwidth among multiple agents is a critical challenge. Conventional policies focus on efficiency metrics, potentially leading to dominance concentration that undermines system diversity and stability. We propose Computable Fair Division (CFD), a framework that reinterprets the Boltzmann-Softmax function not as a selection tool but as a probabilistic resource allocation mechanism, redefining the inverse temperature parameter $β$ as a computable control variable governing the efficiency-fairness balance. Static analysis reveals a Pareto frontier with a near-optimal Stability Corridor where total loss remains approximately constant across policy weights. In the dynamic setting, AHC++ (Adaptive Hard-Cap Controller++) updates $β$ in real time using the error between observed dominance and a policy-specified target as feedback. Simulations show that AHC++ suppresses extreme dominance concentration under exogenous shocks while tracking fairness targets without substantial throughput degradation. Scalability analysis confirms that a 100x increase in agents yields only approximately 5.5x increase in execution time. Code: https://github.com/entrofy-ai/computable-fairness

📄 PDF Abstract BibTeX arXiv:2605.22827

Code (0)

등록된 구현이 없습니다.

Reinforcement Learning with Dynamic Boltzmann Softmax Updates

2019-03-14 · Ling Pan, Qingpeng Cai, Qi Meng, Wei Chen 외

Value function estimation is an important task in reinforcement learning, i.e., prediction. The Boltzmann softmax operator is a natural value estimator and can provide several benefits. However, it does not satisfy the n…

Atari Games Q-Learning reinforcement-learning Reinforcement Learning+1

A Convergent Variant of the Boltzmann Softmax Operator in Reinforcement Learning

2018-09-27 · Ling Pan, Qingpeng Cai, Qi Meng, Wei Chen 외

The Boltzmann softmax operator can trade-off well between exploration and exploitation according to current estimation in an exponential weighting scheme, which is a promising way to address the exploration-exploitation …

Atari Games Q-Learning reinforcement-learning Reinforcement Learning+1

Softmax Deep Double Deterministic Policy Gradients

2020-10-19 · NeurIPS 2020 12 · Ling Pan, Qingpeng Cai, Longbo Huang

A widely-used actor-critic reinforcement learning algorithm for continuous control, Deep Deterministic Policy Gradients (DDPG), suffers from the overestimation problem, which can negatively affect the performance. Althou…

continuous-control Continuous Control

An Alternative Softmax Operator for Reinforcement Learning

2016-12-16 · ICML 2017 8 · Kavosh Asadi, Michael L. Littman

A softmax operator applied to a set of values acts somewhat like the maximization function and somewhat like an average. In sequential decision making, softmax is often used in settings where it is necessary to maximize …

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Modeling Documents with Deep Boltzmann Machines

2013-09-26 · Nitish Srivastava, Ruslan R. Salakhutdinov, Geoffrey E. Hinton

We introduce a Deep Boltzmann Machine model suitable for modeling and extracting latent semantic representations from a large unstructured collection of documents. We overcome the apparent difficulty of training a DBM wi…

Document Classification General Classification Retrieval