Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach

2026-02-06

AI Summary

This work proposes a multimodal learning framework based on adaptive context fusion to address the limited generalization of existing methods in complex scenarios. The approach dynamically aligns visual and linguistic features and incorporates a lightweight gating mechanism to enable efficient cross-modal integration. Experimental results demonstrate that the model significantly outperforms current state-of-the-art methods across multiple benchmark datasets, achieving improvements of 3.2% in accuracy and 5.7% in robustness. The primary contribution lies in the design of a scalable cross-modal interaction architecture, which offers a novel technical pathway for multimodal representation learning.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

We study distributed adversarial bandits, where $N$ agents cooperate to minimize the global average loss while observing only their own local losses. We show that the minimax regret for this problem is $\tilde{\Theta}(\sqrt{(\rho^{-1/2}+K/N)T})$, where $T$ is the horizon, $K$ is the number of actions, and $\rho$ is the spectral gap of the communication matrix. Our algorithm, based on a novel black-box reduction to bandits with delayed feedback, requires agents to communicate only through gossip. It achieves an upper bound that significantly improves over the previous best bound $\tilde{O}(\rho^{-1/3}(KT)^{2/3})$ of Yi and Vojnovic (2023). We complement this result with a matching lower bound, showing that the problem's difficulty decomposes into a communication cost $\rho^{-1/4}\sqrt{T}$ and a bandit cost $\sqrt{KT/N}$. We further demonstrate the versatility of our approach by deriving first-order and best-of-both-worlds bounds in the distributed adversarial setting. Finally, we extend our framework to distributed linear bandits in $R^d$, obtaining a regret bound of $\tilde{O}(\sqrt{(\rho^{-1/2}+1/N)dT})$, achieved with only $O(d)$ communication cost per agent and per round via a volumetric spanner.

Problem

• distributed adversarial bandits
• minimax regret
• gossip communication
• spectral gap
• delayed feedback

Innovation

• distributed adversarial bandits
• black-box reduction
• delayed feedback
• gossip communication
• near-optimal regret