Peter Richtárik

Orcid: 0000-0003-4380-5848

Affiliations:
  • King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia
  • University of Edinburgh, UK (former)
  • Moscow Institute of Physics and Technology (MIPT), Dolgoprudny, Russia (former)
  • Cornell University, Ithaca, NY, USA (former, PhD 2007)


According to our database1, Peter Richtárik authored at least 244 papers between 2010 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Faster Rates for Compressed Federated Learning with Client-Variance Reduction.
SIAM J. Math. Data Sci., March, 2024

Federated Sampling with Langevin Algorithm under Isoperimetry.
Trans. Mach. Learn. Res., 2024

Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation.
CoRR, 2024

Methods for Convex (L<sub>0</sub>,L<sub>1</sub>)-Smooth Optimization: Clipping, Acceleration, and Adaptivity.
CoRR, 2024

Cohort Squeeze: Beyond a Single Communication Round per Cohort in Cross-Device Federated Learning.
CoRR, 2024

Prune at the Clients, Not the Server: Accelerated Sparse Training in Federated Learning.
CoRR, 2024

SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning.
CoRR, 2024

A Unified Theory of Stochastic Proximal Point Methods without Smoothness.
CoRR, 2024

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence.
CoRR, 2024

Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations.
CoRR, 2024

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression.
CoRR, 2024

FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models.
CoRR, 2024

Streamlining in the Riemannian Realm: Efficient Riemannian Optimization with Loopless Variance Reduction.
CoRR, 2024

LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression.
CoRR, 2024

Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity.
CoRR, 2024

Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity.
CoRR, 2024

Correlated Quantization for Faster Nonconvex Distributed Optimization.
CoRR, 2024

Towards a Better Theoretical Understanding of Independent Subnetwork Training.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Understanding Progressive Training Through the Framework of Randomized Coordinate Descent.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization.
J. Optim. Theory Appl., November, 2023

Stochastic distributed learning with gradient quantization and double-variance reduction.
Optim. Methods Softw., January, 2023

Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling.
Trans. Mach. Learn. Res., 2023

AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods.
Trans. Mach. Learn. Res., 2023

Adaptive Compression for Communication-Efficient Distributed Training.
Trans. Mach. Learn. Res., 2023

Better Theory for SGD in the Nonconvex World.
Trans. Mach. Learn. Res., 2023

Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation.
Trans. Mach. Learn. Res., 2023

Personalized Federated Learning with Communication Compression.
Trans. Mach. Learn. Res., 2023

On Biased Compression for Distributed Learning.
J. Mach. Learn. Res., 2023

MAST: Model-Agnostic Sparsified Training.
CoRR, 2023

Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences.
CoRR, 2023

Improving Accelerated Federated Learning with Compression and Importance Sampling.
CoRR, 2023

Clip21: Error Feedback for Gradient Clipping.
CoRR, 2023

Global-QSGD: Practical Floatless Quantization for Distributed Learning with Theoretical Guarantees.
CoRR, 2023

Error Feedback Shines when Features are Rare.
CoRR, 2023

Explicit Personalization and Local Training: Double Communication Acceleration in Federated Learning.
CoRR, 2023

ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression.
CoRR, 2023

TAMUNA: Accelerated Federated Learning with Local Training and Partial Participation.
CoRR, 2023

Federated Learning with Regularized Client Participation.
CoRR, 2023

Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes.
CoRR, 2023

Random Reshuffling with Variance Reduction: New Analysis and Better Rates.
Proceedings of the Uncertainty in Artificial Intelligence, 2023

A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Momentum Provably Improves Error Feedback!
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Guide Through the Zoo of Biased SGD.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance.
Proceedings of the International Conference on Machine Learning, 2023

EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression.
Proceedings of the International Conference on Machine Learning, 2023

DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Kimad: Adaptive Gradient Compression with Bandwidth Awareness.
Proceedings of the 4th International Workshop on Distributed Machine Learning, 2023

Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization.
Proceedings of the 4th International Workshop on Distributed Machine Learning, 2023

Federated Learning is Better with Non-Homomorphic Encryption.
Proceedings of the 4th International Workshop on Distributed Machine Learning, 2023

Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

Catalyst Acceleration of Error Compensated Methods Leads to Better Communication Complexity.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

Can 5th Generation Local Training Methods Support Client Sampling? Yes!
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022
FedShuffle: Recipes for Better Use of Local Work in Federated Learning.
Trans. Mach. Learn. Res., 2022

Optimal Client Sampling for Federated Learning.
Trans. Mach. Learn. Res., 2022

Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization.
SIAM J. Math. Data Sci., 2022

Quasi-Newton methods for machine learning: forget the past, just sample.
Optim. Methods Softw., 2022

Dualize, Split, Randomize: Toward Fast Nonsmooth Optimization Algorithms.
J. Optim. Theory Appl., 2022

Direct nonlinear acceleration.
EURO J. Comput. Optim., 2022

Can 5<sup>th</sup> Generation Local Training Methods Support Client Sampling? Yes!
CoRR, 2022

GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity.
CoRR, 2022

Provably Doubly Accelerated Federated Learning: The First Theoretically Successful Combination of Local Training and Compressed Communication.
CoRR, 2022

Improved Stein Variational Gradient Descent with Importance Weights.
CoRR, 2022

Adaptive Learning Rates for Faster Stochastic Gradient Methods.
CoRR, 2022

Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox.
CoRR, 2022

A Note on the Convergence of Mirrored Stein Variational Gradient Descent under (L<sub>0</sub>, L<sub>1</sub>)-Smoothness Condition.
CoRR, 2022

Federated Optimization Algorithms with Random Reshuffling and Gradient Compression.
CoRR, 2022

Certified Robustness in Federated Learning.
CoRR, 2022

Federated Learning with a Sampling Algorithm under Isoperimetry.
CoRR, 2022

Federated Random Reshuffling with Compression and Variance Reduction.
CoRR, 2022

DASHA: Distributed Nonconvex Optimization with Communication Compression, Optimal Oracle Complexity, and No Client Synchronization.
CoRR, 2022

Shifted compression framework: generalizations and improvements.
Proceedings of the Uncertainty in Artificial Intelligence, 2022

BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with an Inexact Prox.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Accelerated Primal-Dual Gradient Method for Smooth and Convex-Concave Saddle-Point Problems with Bilinear Coupling.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Optimal Algorithms for Decentralized Stochastic Variational Inequalities.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Natural Compression for Distributed Deep Learning.
Proceedings of the Mathematical and Scientific Machine Learning, 2022

MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization.
Proceedings of the Mathematical and Scientific Machine Learning, 2022

A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1.
Proceedings of the International Conference on Machine Learning, 2022

FedNL: Making Newton-Type Methods Applicable to Federated Learning.
Proceedings of the International Conference on Machine Learning, 2022

3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation.
Proceedings of the International Conference on Machine Learning, 2022

ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!
Proceedings of the International Conference on Machine Learning, 2022

Proximal and Federated Random Reshuffling.
Proceedings of the International Conference on Machine Learning, 2022

Permutation Compressors for Provably Faster Distributed Nonconvex Optimization.
Proceedings of the Tenth International Conference on Learning Representations, 2022

IntSGD: Adaptive Floatless Compression of Stochastic Gradients.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information.
Proceedings of the Tenth International Conference on Learning Representations, 2022

An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021
Revisiting Randomized Gossip Algorithms: General Framework, Convergence Rates and Novel Block and Accelerated Protocols.
IEEE Trans. Inf. Theory, 2021

Stochastic quasi-gradient methods: variance reduction via Jacobian sketching.
Math. Program., 2021

L-SVRG and L-Katyusha with Arbitrary Sampling.
J. Mach. Learn. Res., 2021

EF21 with Bells & Whistles: Practical Algorithmic Extensions of Modern Error Feedback.
CoRR, 2021

FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learning.
CoRR, 2021

A Field Guide to Federated Optimization.
CoRR, 2021

Smoothness-Aware Quantization Techniques.
CoRR, 2021

Complexity Analysis of Stein Variational Gradient Descent Under Talagrand's Inequality T1.
CoRR, 2021

ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computation.
CoRR, 2021

AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods.
CoRR, 2021

IntSGD: Floatless Compression of Stochastic Gradients.
CoRR, 2021

Accelerated Bregman proximal gradient methods for relatively smooth convex optimization.
Comput. Optim. Appl., 2021

Fastest rates for stochastic mirror descent methods.
Comput. Optim. Appl., 2021

Scaling Distributed Machine Learning with In-Network Aggregation.
Proceedings of the 18th USENIX Symposium on Networked Systems Design and Implementation, 2021

Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Error Compensated Distributed SGD Can Be Accelerated.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Stochastic Sign Descent Methods: New Algorithms and Better Theory.
Proceedings of the 38th International Conference on Machine Learning, 2021

PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization.
Proceedings of the 38th International Conference on Machine Learning, 2021

ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks.
Proceedings of the 38th International Conference on Machine Learning, 2021

Distributed Second Order Methods with Fast Rates and Compressed Communication.
Proceedings of the 38th International Conference on Machine Learning, 2021

MARINA: Faster Non-Convex Distributed Learning with Compression.
Proceedings of the 38th International Conference on Machine Learning, 2021

A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning.
Proceedings of the 9th International Conference on Learning Representations, 2021

FL_PyTorch: optimization research simulator for federated learning.
Proceedings of the DistributedML '21: Proceedings of the 2nd ACM International Workshop on Distributed Machine Learning, 2021

A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Hyperparameter Transfer Learning with Adaptive Complexity.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Local SGD: Unified Theory and New Efficient Methods.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
Best Pair Formulation & Accelerated Scheme for Non-Convex Principal Component Pursuit.
IEEE Trans. Signal Process., 2020

Convergence Analysis of Inexact Randomized Iterative Methods.
SIAM J. Sci. Comput., 2020

Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory.
SIAM J. Matrix Anal. Appl., 2020

Stochastic Three Points Method for Unconstrained Smooth Minimization.
SIAM J. Optim., 2020

Variance-Reduced Methods for Machine Learning.
Proc. IEEE, 2020

Optimal Gradient Compression for Distributed and Federated Learning.
CoRR, 2020

Distributed Proximal Splitting Algorithms with Rates and Acceleration.
CoRR, 2020

A Unified Analysis of Stochastic Gradient Methods for Nonconvex Federated Optimization.
CoRR, 2020

Adaptive Learning of the Optimal Mini-Batch Size of SGD.
CoRR, 2020

Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms.
CoRR, 2020

On the Convergence Analysis of Asynchronous SGD for Solving Consistent Linear Systems.
CoRR, 2020

Fast Linear Convergence of Randomized BFGS.
CoRR, 2020

Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor.
CoRR, 2020

Federated Learning of a Mixture of Global and Local Models.
CoRR, 2020

Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods.
Comput. Optim. Appl., 2020

99% of Worker-Master Communication in Distributed Optimization Is Not Needed.
Proceedings of the Thirty-Sixth Conference on Uncertainty in Artificial Intelligence, 2020

Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Random Reshuffling: Simple Analysis with Vast Improvements.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Lower Bounds and Optimal Algorithms for Personalized Federated Learning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Linearly Converging Error Compensated SGD.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

From Local SGD to Local Fixed-Point Methods for Federated Learning.
Proceedings of the 37th International Conference on Machine Learning, 2020

Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization.
Proceedings of the 37th International Conference on Machine Learning, 2020

Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems.
Proceedings of the 37th International Conference on Machine Learning, 2020

Stochastic Subspace Cubic Newton Method.
Proceedings of the 37th International Conference on Machine Learning, 2020

A Stochastic Derivative Free Optimization Method with Momentum.
Proceedings of the 8th International Conference on Learning Representations, 2020

Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop.
Proceedings of the Algorithmic Learning Theory, 2020

Revisiting Stochastic Extragradient.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Tighter Theory for Local SGD on Identical and Heterogeneous Data.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Randomized Projection Methods for Convex Feasibility: Conditioning and Convergence Rates.
SIAM J. Optim., 2019

New Convergence Aspects of Stochastic Gradient Algorithms.
J. Mach. Learn. Res., 2019

Distributed Fixed Point Methods with Compressed Iterates.
CoRR, 2019

Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates.
CoRR, 2019

Better Communication Complexity for Local SGD.
CoRR, 2019

Gradient Descent with Compressed Iterates.
CoRR, 2019

First Analysis of Local GD on Heterogeneous Data.
CoRR, 2019

One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods.
CoRR, 2019

99% of Parallel Optimization is Inevitably a Waste of Time.
CoRR, 2019

SGD: General Analysis and Improved Rates.
CoRR, 2019

A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion.
CoRR, 2019

Distributed Learning with Compressed Gradient Differences.
CoRR, 2019

Online and Batch Supervised Background Estimation Via L1 Regression.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2019

Stochastic Convolutional Sparse Coding.
Proceedings of the 24th International Symposium on Vision, Modeling, and Visualization, 2019

Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

RSN: Randomized Subspace Newton.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

SGD with Arbitrary Sampling: General Analysis and Improved Rates.
Proceedings of the 36th International Conference on Machine Learning, 2019

SAGA with Arbitrary Sampling.
Proceedings of the 36th International Conference on Machine Learning, 2019

Nonconvex Variance Reduced Optimization with Arbitrary Sampling.
Proceedings of the 36th International Conference on Machine Learning, 2019

Provably Accelerated Randomized Gossip Algorithms.
Proceedings of the IEEE International Conference on Acoustics, 2019

Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

A Nonconvex Projection Method for Robust PCA.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018
Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications.
SIAM J. Optim., 2018

On the complexity of parallel coordinate descent.
Optim. Methods Softw., 2018

Importance Sampling for Minibatches.
J. Mach. Learn. Res., 2018

Randomized Distributed Mean Estimation: Accuracy vs. Communication.
Frontiers Appl. Math. Stat., 2018

Weighted Low-Rank Approximation of Matrices and Background Modeling.
CoRR, 2018

Matrix Completion Under Interval Uncertainty: Highlights.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2018

Stochastic Spectral and Conjugate Descent Methods.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

SEGA: Variance Reduction via Gradient Sketching.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

SGD and Hogwild! Convergence Without the Bounded Gradients Assumption.
Proceedings of the 35th International Conference on Machine Learning, 2018

Randomized Block Cubic Newton Method.
Proceedings of the 35th International Conference on Machine Learning, 2018

Coordinate Descent Faceoff: Primal or Dual?
Proceedings of the Algorithmic Learning Theory, 2018

Accelerated Gossip via Stochastic Heavy Ball Method.
Proceedings of the 56th Annual Allerton Conference on Communication, 2018

2017
Randomized Quasi-Newton Updates Are Linearly Convergent Matrix Inversion Algorithms.
SIAM J. Matrix Anal. Appl., 2017

Distributed optimization with arbitrary local solvers.
Optim. Methods Softw., 2017

Semi-stochastic coordinate descent.
Optim. Methods Softw., 2017

Semi-Stochastic Gradient Descent Methods.
Frontiers Appl. Math. Stat., 2017

Matrix completion under interval uncertainty.
Eur. J. Oper. Res., 2017

Linearly convergent stochastic heavy ball method for minimizing generalization error.
CoRR, 2017

A Batch-Incremental Video Background Estimation Model Using Weighted Low-Rank Approximation of Matrices.
Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops, 2017

2016
Optimization in High Dimensions via Accelerated, Parallel, and Proximal Coordinate Descent.
SIAM Rev., 2016

Coordinate descent with arbitrary sampling II: expected separable overapproximation.
Optim. Methods Softw., 2016

Coordinate descent with arbitrary sampling I: algorithms and complexity.
Optim. Methods Softw., 2016

On optimal probabilities in stochastic coordinate descent methods.
Optim. Lett., 2016

Parallel coordinate descent methods for big data optimization.
Math. Program., 2016

Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting.
IEEE J. Sel. Top. Signal Process., 2016

Inexact Coordinate Descent: Complexity and Preconditioning.
J. Optim. Theory Appl., 2016

Distributed Coordinate Descent Method for Learning with Big Data.
J. Mach. Learn. Res., 2016

AIDE: Fast and Communication Efficient Distributed Optimization.
CoRR, 2016

Federated Learning: Strategies for Improving Communication Efficiency.
CoRR, 2016

Federated Optimization: Distributed Machine Learning for On-Device Intelligence.
CoRR, 2016

Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling.
Proceedings of the 33nd International Conference on Machine Learning, 2016

SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Stochastic Block BFGS: Squeezing More Curvature out of Data.
Proceedings of the 33nd International Conference on Machine Learning, 2016

A new perspective on randomized gossip algorithms.
Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing, 2016

2015
Randomized Iterative Methods for Linear Systems.
SIAM J. Matrix Anal. Appl., 2015

Accelerated, Parallel, and Proximal Coordinate Descent.
SIAM J. Optim., 2015

Separable approximations and decomposition methods for the augmented Lagrangian.
Optim. Methods Softw., 2015

Distributed Mini-Batch SDCA.
CoRR, 2015

Stochastic Dual Ascent for Solving Linear Systems.
CoRR, 2015

Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses.
CoRR, 2015

Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Adding vs. Averaging in Distributed Primal-Dual Optimization.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Stochastic Dual Coordinate Ascent with Adaptive Probabilities.
Proceedings of the 32nd International Conference on Machine Learning, 2015

2014
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function.
Math. Program., 2014

Inequality-Constrained Matrix Completion: Adding the Obvious Helps!
CoRR, 2014

Randomized Dual Coordinate Ascent with Arbitrary Sampling.
CoRR, 2014

Simple Complexity Analysis of Direct Search.
CoRR, 2014

mS2GD: Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting.
CoRR, 2014

Fast distributed coordinate descent for non-strongly convex losses.
Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing, 2014

2013
TOP-SPIN: TOPic discovery via Sparse Principal component INterference.
CoRR, 2013

Smooth minimization of nonsmooth functions with parallel coordinate descent methods.
CoRR, 2013

Mini-Batch Primal and Dual Methods for SVMs.
Proceedings of the 30th International Conference on Machine Learning, 2013

2012
Approximate Level Method for Nonsmooth Convex Minimization.
J. Optim. Theory Appl., 2012

Alternating Maximization: Unifying Framework for 8 Sparse PCA Formulations and Efficient Parallel Codes
CoRR, 2012

Optimal diagnostic tests for sporadic Creutzfeldt-Jakob disease based on support vector machine classification of RT-QuIC data
CoRR, 2012

2011
Improved Algorithms for Convex Minimization in Relative Scale.
SIAM J. Optim., 2011

Efficient Serial and Parallel Coordinate Descent Methods for Huge-Scale Truss Topology Design.
Proceedings of the Operations Research Proceedings 2011, Selected Papers of the International Conference on Operations Research (OR 2011), August 30, 2011

2010
Generalized Power Method for Sparse Principal Component Analysis.
J. Mach. Learn. Res., 2010


  Loading...