paper-with-me

홈 › Papers

Multitask Online Learning: Listen to the Neighborhood Buzz

2023-10-26 · Juliette Achddou, Nicolò Cesa-Bianchi, Pierre Laforgue

We study multitask online learning in a setting where agents can only exchange information with their neighbors on an arbitrary communication network. We introduce $\texttt{MT-CO}_2\texttt{OL}$, a decentralized algorithm for this setting whose regret depends on the interplay between the task similarities and the network structure. Our analysis shows that the regret of $\texttt{MT-CO}_2\texttt{OL}$ is never worse (up to constants) than the bound obtained when agents do not share information. On the other hand, our bounds significantly improve when neighboring agents operate on similar tasks. In addition, we prove that our algorithm can be made differentially private with a negligible impact on the regret. Finally, we provide experimental support for our theory.

📄 PDF Abstract BibTeX arXiv:2310.17385

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference

2024-10-30 · Junqi Zhao, Zhijin Fang, Shu Li, Shaohui Yang 외

Large language models (LLMs) are essential in natural language processing but often struggle with inference speed and computational efficiency, limiting real-time deployment. The key-value (KV) cache mechanism reduces co…

Computational EfficiencyQuestion AnsweringText Summarization

A Coevolutionary Variable Neighborhood Search Algorithm for Discrete Multitasking (CoVNS): Application to Community Detection over Graphs

2020-09-30 · Eneko Osaba, Esther Villar-Rodriguez, Javier Del Ser

The main goal of the multitasking optimization paradigm is to solve multiple and concurrent optimization tasks in a simultaneous way through a single search process. For attaining promising results, potential complementa…

Community Detection

Can Large Language Models Understand Internet Buzzwords Through User-Generated Content

2025-05-21 · Chen Huang, Junkai Luo, Xinzuo Wang, Wenqiang Lei 외

The massive user-generated content (UGC) available in Chinese social media is giving rise to the possibility of studying internet buzzwords. In this paper, we study if large language models (LLMs) can generate accurate d…

Multitask Training with Text Data for End-to-End Speech Recognition

2020-10-27 · Peidong Wang, Tara N. Sainath, Ron J. Weiss

We propose a multitask training method for attention-based end-to-end speech recognition models. We regularize the decoder in a listen, attend, and spell model by multitask training it on both audio-text and text-only da…

DecoderLanguage ModelingLanguage Modellingspeech-recognition+1

LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs

2025-05-24 · Pooneh Mousavi, Shubham Gupta, Cem Subakan, Mirco Ravanelli

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-language tasks is challenging due to dif…

Diversity