paper-with-me

Papers

Exact Subspace Diffusion for Decentralized Multitask Learning

2023-04-14 · Shreya Wadehra, Roula Nassif, Stefan Vlaski

Classical paradigms for distributed learning, such as federated or decentralized gradient descent, employ consensus mechanisms to enforce homogeneity among agents. While these strategies have proven effective in i.i.d. scenarios, they can result in significant performance degradation when agents follow heterogeneous objectives or data. Distributed strategies for multitask learning, on the other hand, induce relationships between agents in a more nuanced manner, and encourage collaboration without enforcing consensus. We develop a generalization of the exact diffusion algorithm for subspace constrained multitask learning over networks, and derive an accurate expression for its mean-squared deviation when utilizing noisy gradient approximations. We verify numerically the accuracy of the predicted performance expressions, as well as the improved performance of the proposed approach over alternatives based on approximate projections.

📄 PDF Abstract BibTeX arXiv:2304.07358

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Decentralized Multitask Learning over Learned Task Graphs

2026-08-27 · Zirui Wan, Stefan Vlaski arxiv

This paper investigates decentralized multitask learning over networks when the underlying task relationships are unknown. While existing graph-regularized multitask frameworks typically assume a known structure, practic…

Quantization for decentralized learning under subspace constraints

2022-09-16 · Roula Nassif, Stefan Vlaski, Marco Carpentiero, Vincenzo Matta 외

In this paper, we consider decentralized optimization problems where agents have individual cost functions to minimize subject to subspace constraints that require the minimizers across the network to lie in low-dimensio…

Quantization

Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD

2021-05-17 · Kun Yuan, Sulaiman A. Alghunaim, Xinmeng Huang

We consider the decentralized stochastic optimization problems, where a network of $n$ nodes, each owning a local cost function, cooperate to find a minimizer of the globally-averaged cost. A widely studied decentralized…

Stochastic Optimization

Subspace Diffusion Generative Models

2022-05-03 · Bowen Jing, Gabriele Corso, Renato Berlinghieri, Tommi Jaakkola

Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We question whether it is necessary to run this entire process at high dimensionality and incur all …

DenoisingImage Generation

SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization

2024-11-21 · Shuchen Zhu, Boao Kong, Songtao Lu, Xinmeng Huang 외

This paper studies decentralized bilevel optimization, in which multiple agents collaborate to solve problems involving nested optimization structures with neighborhood communications. Most existing literature primarily …

Bilevel Optimization