activity
20242026
most citedTackling heavy-tailed noise in distributed estimation: Asymptotic performance and tradeoffs

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts

Jihoon Lee, Hoyeon Moon, Kevin Zhai +6

Diffusion-based large language models (dLLMs) are trained flexibly to model extreme dependence in the data distribution; however, how to best utilize this information at inference…

cs.LG2025

Federated Multi-Objective Learning with Controlled Pareto Frontiers

Jiansheng Rao, Jiayi Li, Zhizhi Gong +2

Federated learning (FL) is a widely adopted paradigm for privacy-preserving model training, but FedAvg optimise for the majority while under-serving minority clients. Existing meth…

cs.LG2025

Large Deviation Upper Bounds and Improved MSE Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry

Aleksandar Armacki, Shuhua Yu, Dragana Bajovic +2

We study large deviation upper bounds and mean-squared error (MSE) guarantees of a general framework of nonlinear stochastic gradient methods in the online setting, in the presence…

cs.LG2025

Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees

Aleksandar Armacki, Shuhua Yu, Pranay Sharma +4

We study high-probability convergence in online learning, in the presence of heavy-tailed noise. To combat the heavy tails, a general framework of nonlinear SGD methods is consider…

cs.LG2025

Distributed Sign Momentum with Local Steps for Training Transformers

Shuhua Yu, Ding Zhou, Cong Xie +4

Pre-training Transformer models is resource-intensive, and recent studies have shown that sign momentum is an efficient technique for training large-scale deep learning models, par…

cs.LG2024

A Unified Framework for Center-based Clustering of Distributed Data

Aleksandar Armacki, Dragana Bajović, Dušan Jakovetić +1

We develop a family of distributed center-based clustering algorithms that work over networks of users. In the proposed scenario, users contain a local dataset and communicate only…