134 citations · 553 across the 48 of their papers we have counts for
7 papers · 1 filter
Parallel Inexact Levenberg-Marquardt Method for Nearly-Separable Nonlinear Least Squares
Lidija Fodor, Dusan Jakovetic, Natasa Krejic +1
Motivated by localization problems such as cadastral maps refinements, we consider a generic Nonlinear Least Squares (NLS) problem of minimizing an aggregate squared fit across all…
High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise
Aleksandar Armacki, Pranay Sharma, Gauri Joshi +3
We study high-probability convergence guarantees of learning on streaming data in the presence of heavy-tailed noise. In the proposed scenario, the model is updated in an online fa…
Smoothed Gradient Clipping and Error Feedback for Decentralized Optimization under Symmetric Heavy-Tailed Noise
Shuhua Yu, Dusan Jakovetic, Soummya Kar
Motivated by understanding and analysis of large-scale machine learning under heavy-tailed gradient noise, we study decentralized optimization with gradient clipping, i.e., in whic…
Distributed Inexact Newton Method with Adaptive Step Sizes
Dusan Jakovetic, Natasa Krejic, Greta Malaspina
We consider two formulations for distributed optimization wherein agents in a generic connected network solve a problem of common interest: distributed personalized optimizatio…
Accurate and Interpretable Solution of the Inverse Rig for Realistic Blendshape Models with Quadratic Corrective Terms
Stevo Racković, Cláudia Soares, Dušan Jakovetić +1
We propose a new model-based algorithm solving the inverse rig problem in facial animation retargeting, exhibiting higher accuracy of the fit and sparser, more interpretable weight…
High-fidelity Interpretable Inverse Rig: An Accurate and Sparse Solution Optimizing the Quartic Blendshape Model
Stevo Racković, Cláudia Soares, Dušan Jakovetić +1
We propose a method to fit arbitrarily accurate blendshape rig models by solving the inverse rig problem in realistic human face animation. The method considers blendshape models w…