PPaperPicks

Peter Richtárik

King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia

32 papers at tracked venues · 24 at CORE A* · active 2024–2025

DBLP profile ↗ORCID 0000-0003-4380-5848 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×12ICLR ×7ICML ×4UAI ×3AISTATS ×2AAAI ×1ECAI ×1ECML-PKDD ×1NAACL ×1

Frequent coauthors

Arto Maranjyan
DBLP profile ↗ORCID search ↗
×3
Alexander Tyurin
DBLP profile ↗ORCID search ↗
×3
Vladimir Malinovskii
DBLP profile ↗ORCID search ↗
×2
Yury Demidovich
DBLP profile ↗ORCID search ↗
×2
Eduard Gorbunov
DBLP profile ↗ORCID search ↗
×2
Abdurakhmon Sadiev
DBLP profile ↗ORCID search ↗
×2
Hanmin Li
DBLP profile ↗ORCID search ↗
×2
Ali Beikmohammadi
DBLP profile ↗ORCID search ↗
×1
Andrei Panferov
DBLP profile ↗ORCID search ↗
×1
Avetik G. Karagulyan
DBLP profile ↗ORCID search ↗
×1
Sarit Khirirat
DBLP profile ↗ORCID search ↗
×1
Laurent Condat
DBLP profile ↗ORCID search ↗
×1

Papers

  1. ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning
    ICML 2025 ·
    Arto Maranjyan
    DBLP profile ↗ORCID search ↗
  2. Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis
    ECML-PKDD 2025 ·
    Ali Beikmohammadi
    DBLP profile ↗ORCID search ↗
  3. Correlated Quantization for Faster Nonconvex Distributed Optimization
    UAI 2025 ·
    Andrei Panferov
    DBLP profile ↗ORCID search ↗
  4. ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression
    UAI 2025 ·
    Avetik G. Karagulyan
    DBLP profile ↗ORCID search ↗
  5. Error Feedback under (L0, L1)-Smoothness: Normalization and Momentum
    NeurIPS 2025 ·
    Sarit Khirirat
    DBLP profile ↗ORCID search ↗
  6. HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
    NAACL 2025 ·
    Vladimir Malinovskii
    DBLP profile ↗ORCID search ↗
  7. LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression
    ICLR 2025 ·
    Laurent Condat
    DBLP profile ↗ORCID search ↗
  8. Local Curvature Descent: Squeezing More Curvature out of Standard and Polyak Gradient Descent
    NeurIPS 2025 · Peter Richtárik
  9. MAST: model-agnostic sparsified training
    ICLR 2025 ·
    Yury Demidovich
    DBLP profile ↗ORCID search ↗
  10. Methods for Convex (L0, L1)-Smooth Optimization: Clipping, Acceleration, and Adaptivity
    ICLR 2025 ·
    Eduard Gorbunov
    DBLP profile ↗ORCID search ↗
  11. Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
    ICLR 2025 ·
    Yury Demidovich
    DBLP profile ↗ORCID search ↗
  12. MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times
    UAI 2025 ·
    Arto Maranjyan
    DBLP profile ↗ORCID search ↗
  13. Quantize Once, Train Fast: Allreduce-Compatible Compression with Provable Guarantees
    ECAI 2025 ·
    Jihao Xin
    DBLP profile ↗ORCID search ↗
  14. Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity
    ICML 2025 ·
    Arto Maranjyan
    DBLP profile ↗ORCID search ↗
  15. Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
    NeurIPS 2025 ·
    Abdurakhmon Sadiev
    DBLP profile ↗ORCID search ↗
  16. Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
    NeurIPS 2024 ·
    Grigory Malinovsky
    DBLP profile ↗ORCID search ↗
  17. Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates
    AISTATS 2024 ·
    Ahmad Rammal
    DBLP profile ↗ORCID search ↗
  18. Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
    ICLR 2024 ·
    Hanmin Li
    DBLP profile ↗ORCID search ↗
  19. Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
    NeurIPS 2024 ·
    Abdurakhmon Sadiev
    DBLP profile ↗ORCID search ↗
  20. Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants
    ICLR 2024 · Peter Richtárik
  21. FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
    ICLR 2024 ·
    Kai Yi
    DBLP profile ↗ORCID search ↗
  22. Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations
    NeurIPS 2024 ·
    Alexander Tyurin
    DBLP profile ↗ORCID search ↗
  23. High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise
    ICML 2024 ·
    Eduard Gorbunov
    DBLP profile ↗ORCID search ↗
  24. Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity
    NeurIPS 2024 ·
    Kaja Gruntkowska
    DBLP profile ↗ORCID search ↗
  25. MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
    NeurIPS 2024 ·
    Ionut-Vlad Modoranu
    DBLP profile ↗ORCID search ↗
  26. Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization
    AAAI 2024 ·
    Soumia Boucherouite
    DBLP profile ↗ORCID search ↗
  27. On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization
    NeurIPS 2024 ·
    Alexander Tyurin
    DBLP profile ↗ORCID search ↗
  28. PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
    NeurIPS 2024 ·
    Vladimir Malinovskii
    DBLP profile ↗ORCID search ↗
  29. Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity
    NeurIPS 2024 ·
    Alexander Tyurin
    DBLP profile ↗ORCID search ↗
  30. The Power of Extrapolation in Federated Learning
    NeurIPS 2024 ·
    Hanmin Li
    DBLP profile ↗ORCID search ↗
  31. Towards a Better Theoretical Understanding of Independent Subnetwork Training
    ICML 2024 ·
    Egor Shulgin
    DBLP profile ↗ORCID search ↗
  32. Understanding Progressive Training Through the Framework of Randomized Coordinate Descent
    AISTATS 2024 ·
    Rafal Szlendak
    DBLP profile ↗ORCID search ↗