3 papers
cs.LG2025
Smoothed Normalization for Efficient Distributed Private Optimization
Egor Shulgin, Sarit Khirirat, Peter Richtárik
Federated learning enables training machine learning models while preserving the privacy of participants. Surprisingly, there is no differentially private distributed method for sm…
cs.LG2025
A Novel Unified Parametric Assumption for Nonconvex Optimization
Artem Riabinin, Ahmed Khaled, Peter Richtárik
Nonconvex optimization is central to modern machine learning, but the general framework of nonconvex optimization yields weak convergence guarantees that are too pessimistic compar…
cs.LG2025
Symmetric Pruning of Large Language Models
Kai Yi, Peter Richtárik
Popular post-training pruning methods such as Wanda and RIA are known for their simple, yet effective, designs that have shown exceptional empirical performance. Wanda optimizes pe…