Tootfinder

Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approach
Yueyang Quan, Chang Wang, Shengjie Zhai, Minghong Fang, Zhuqing Liu
https://arxiv.org/abs/2508.07505

Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approach
Decentralized min-max optimization allows multi-agent systems to collaboratively solve global min-max optimization problems by facilitating the exchange of model updates among neighboring agents, eliminating the need for a central server. However, sharing model updates in such systems carry a risk of exposing sensitive data to inference attacks, raising significant privacy concerns. To mitigate these privacy risks, differential privacy (DP) has become a widely adopted technique for safeguarding…

Bayesian Double Descent
Nick Polson, Vadim Sokolov
https://arxiv.org/abs/2507.07338 https://arxiv.org/pdf/2507.07338

Bayesian Double Descent
Double descent is a phenomenon of over-parameterized statistical models. Our goal is to view double descent from a Bayesian perspective. Over-parameterized models such as deep neural networks have an interesting re-descending property in their risk characteristics. This is a recent phenomenon in machine learning and has been the subject of many studies. As the complexity of the model increases, there is a U-shaped region corresponding to the traditional bias-variance trade-off, but then as the …

Distributed and Decentralised Training: Technical Governance Challenges in a Shifting AI Landscape
Jakub Kry\'s, Yashvardhan Sharma, Janet Egan
https://arxiv.org/abs/2507.07765

Distributed and Decentralised Training: Technical Governance Challenges in a Shifting AI Landscape
Advances in low-communication training algorithms are enabling a shift from centralised model training to compute setups that are either distributed across multiple clusters or decentralised via community-driven contributions. This paper distinguishes these two scenarios - distributed and decentralised training - which are little understood and often conflated in policy discourse. We discuss how they could impact technical AI governance through an increased risk of compute structuring, capabili…

#AI

OpenRouter
The unified interface for LLMs. Find the best models & prices for your prompts

Order-disorder-order transitions and winning margins' scaling in kinetic exchange opinion model
Soumyajyoti Biswas, Mandhalapu Sree Annapurna, Venkatasubbaiah Jakkampudi, Dushyanth Yarlagadda, Bhargav Thota
https://arxiv.org/abs/2508.06237

Order-disorder-order transitions and winning margins' scaling in kinetic exchange opinion model
The kinetic exchange opinion model shows a well-studied order disorder transition as the noise parameter, representing discord between interacting agents, is increased. A further increase in the noise drives the model, in low dimensions, to an extreme segregation ordering through a transition of similar nature. The scaling behavior of the winning margins have distinct features in the ordered and disordered phases that are similar to the observations noted recently in election data in various co…

Value Function Approximation for Nonlinear MPC: Learning a Terminal Cost Function with a Descent Property
T. M. J. T. Baltussen, C. A. Orrico, A. Katriniok, W. P. M. H. Heemels, D. Krishnamoorthy
https://arxiv.org/abs/2508.05804

Value Function Approximation for Nonlinear MPC: Learning a Terminal Cost Function with a Descent Property
We present a novel method to synthesize a terminal cost function for a nonlinear model predictive controller (MPC) through value function approximation using supervised learning. Existing methods enforce a descent property on the terminal cost function by construction, thereby restricting the class of terminal cost functions, which in turn can limit the performance and applicability of the MPC. We present a method to approximate the true cost-to-go with a general function approximator that is c…

Generalization Error Analysis for Attack-Free and Byzantine-Resilient Decentralized Learning with Data Heterogeneity
Haoxiang Ye, Tao Sun, Qing Ling
https://arxiv.org/abs/2506.09438

Generalization Error Analysis for Attack-Free and Byzantine-Resilient Decentralized Learning with Data Heterogeneity
Decentralized learning, which facilitates joint model training across geographically scattered agents, has gained significant attention in the field of signal and information processing in recent years. While the optimization errors of decentralized learning algorithms have been extensively studied, their generalization errors remain relatively under-explored. As the generalization errors reflect the scalability of trained models on unseen data and are crucial in determining the performance of …

DSFL: A Dual-Server Byzantine-Resilient Federated Learning Framework via Group-Based Secure Aggregation
Charuka Herath, Yogachandran Rahulamathavan, Varuna De Silva, Sangarapillai Lambotharan
https://arxiv.org/abs/2509.08449

DSFL: A Dual-Server Byzantine-Resilient Federated Learning Framework via Group-Based Secure Aggregation
Federated Learning (FL) enables decentralized model training without sharing raw data, offering strong privacy guarantees. However, existing FL protocols struggle to defend against Byzantine participants, maintain model utility under non-independent and identically distributed (non-IID) data, and remain lightweight for edge devices. Prior work either assumes trusted hardware, uses expensive cryptographic tools, or fails to address privacy and robustness simultaneously. We propose DSFL, a Dual-S…

A Game-Theoretic Foundation for Bitcoin's Price: A Security-Utility Equilibrium
Liang Chen
https://arxiv.org/abs/2508.06071 https://arxiv.org/pdf/2508.…

A Game-Theoretic Foundation for Bitcoin's Price: A Security-Utility Equilibrium
This paper introduces a structural game-theoretic model to value decentralized digital assets like Bitcoin. Instead of relying on speculative beliefs, it frames the asset's price within a Rational-Expectations Security-Utility Nash Equilibrium (RESUNE). This equilibrium is a fixed point where the market-clearing price dictates the hash rate through a free-entry mining model, which in turn endogenously sets the network's security. The security, defined as one minus the probability of a 51% attac…

Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics
Dikshant Sagar, Kaiwen Yu, Alejandro Yankelevich, Jianming Bian, Pierre Baldi
https://arxiv.org/abs/2509.08461

Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics
Recent advances in Large Language Models (LLMs) have demonstrated their remarkable capacity to process and reason over structured and unstructured data modalities beyond natural language. In this work, we explore the applications of Vision Language Models (VLMs), specifically a fine-tuned variant of LLaMa 3.2, to the task of identifying neutrino interactions in pixelated detector data from high-energy physics (HEP) experiments. We benchmark this model against a state-of-the-art convolutional ne…