Peter Richtárik

Kootenay Association for Science & Technology — Canada

Computer Science · Physical Sciences

48h-index13.0kcitations422works0.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Stochastic Gradient Optimization Techniques(291), Sparse and Compressive Sensing Techniques(219), Privacy-Preserving Technologies in Data(88), Advanced Optimization Algorithms Research(41), Markov Chains and Monte Carlo Methods(34)

Publications422 total

First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
arXiv (Cornell University)·2025Open Access
First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
ArXiv.org·2025Open Access
Tight Lower Bounds and Optimal Algorithms for Stochastic Nonconvex Optimization with Heavy-Tailed Noise
ArXiv.org·2025Open Access
Tight Lower Bounds and Optimal Algorithms for Stochastic Nonconvex Optimization with Heavy-Tailed Noise
arXiv (Cornell University)·2025Open Access
Better LMO-based Momentum Methods with Second-Order Information
arXiv (Cornell University)·2025Open Access
Beyond the Ideal: Analyzing the Inexact Muon Update
arXiv (Cornell University)·2025Open Access
Quantize Once, Train Fast: Allreduce-Compatible Compression with Provable Guarantees
Frontiers in artificial intelligence and applications·2025Open Access
Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
arXiv (Cornell University)·2025Open Access
Drop-Muon: Update Less, Converge Faster
arXiv (Cornell University)·2025Open Access
Error Feedback for Muon and Friends
arXiv (Cornell University)·2025Open Access
Non-Euclidean Broximal Point Method: A Blueprint for Geometry-Aware Optimization
arXiv (Cornell University)·2025Open Access
Local SGD and Federated Averaging Through the Lens of Time Complexity
arXiv (Cornell University)·2025Open Access
Convergence Analysis of the PAGE Stochastic Algorithm for Weakly Convex Finite-Sum Optimization
arXiv (Cornell University)·2025Open Access
Handling Device Heterogeneity in Federated Learning: The First Optimal Parallel SGD in the Presence of Data, Compute and Communication Heterogeneity
2025· 1 cited
Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)
arXiv (Cornell University)·2025Open Access
The Stochastic Multi-Proximal Method for Nonsmooth Optimization
arXiv (Cornell University)·2025Open Access
Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression
arXiv (Cornell University)·2025Open Access
Global-QSGD: Allreduce-Compatible Quantization for Distributed Learning with Theoretical Guarantees
2025· 1 citedOpen Access
Smoothed Normalization for Efficient Distributed Private Optimization
arXiv (Cornell University)·2025Open Access
Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy
arXiv (Cornell University)·2025Open Access
page 1 of 22Next →

Frequent Co-authors

Martin Takáč(17), Jakub Konečný(10), Samuel Horváth(6), Zheng Qu(6), Martin Jaggi(4), Virginia Smith(4), H. Brendan McMahan(3), Filip Hanzely(3), Chenxin Ma(3), Michael I. Jordan(3), Konstantin Mishchenko(3), Felix X. Yu(2), Ananda Theertha Suresh(2), Olivier Fercoq(2), Sashank J. Reddi(2), Sebastian U. Stich(2), Marco Canini(2), Chen-Yu Ho(2), Nicolas Loizou(2), Avleen S. Bijral(2)