2 citations · 2 across the 8 of their papers we have counts for
9 papers
Dialect-Robust Speech Language Models with Synthetic Pseudo-Dialect Augmentation
Shunsuke Mitsumori, Tomoya Mizumoto, Yusuke Fujita
Speech Language Model (SLM) performance often degrades on dialects due to data scarcity. Conventional text-to-speech (TTS) augmentation struggles to cover diverse dialects as it re…
A Unified Zeroth-Order Approach for Decentralized Minimax Optimization
Haoyuan Cai, Yike Zhao, Aleksandar Armacki +2
We propose ZOMA, a unified Zeroth-Order decentralized accelerated MinimAx framework for multi-agent nonconvex Polyak--Łojasiewicz minimax optimization. The proposed framework only…
High-Probability Convergence in Decentralized Stochastic Optimization with Gradient Tracking
Aleksandar Armacki, Haoyuan Cai, Ali H. Sayed
We study high-probability (HP) convergence guarantees in decentralized stochastic optimization, where multiple agents collaborate to jointly train a model over a network. Existing…
Distributed Gradient Clustering: Convergence and the Effect of Initialization
Aleksandar Armacki, Himkant Sharma, Dragana Bajović +3
We study the effects of center initialization on the performance of a family of distributed gradient-based clustering algorithms introduced in [1], that work over connected network…
Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization
Aleksandar Armacki, Dragana Bajović, Dušan Jakovetić +2
The study of tail behaviour of SGD-induced processes has been attracting a lot of interest, due to offering strong guarantees with respect to individual runs of an algorithm. While…
High-Probability Convergence Guarantees of Decentralized SGD
Aleksandar Armacki, Ali H. Sayed
Convergence in high-probability (HP) has attracted increasing interest, due to implying exponentially decaying tail bounds and strong guarantees for individual runs of an algorithm…
Sharp High-Probability Rates for Nonlinear SGD under Heavy-Tailed Noise via Symmetrization
Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic +1
We study convergence in high-probability of SGD-type methods in non-convex optimization and the presence of heavy-tailed noise. To combat the heavy-tailed noise, a general black-bo…
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…
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…