PaperHub

Peter Richtárik

~Peter_Richtárik1

48
论文总数
24.0
年均投稿
5.5
平均评分
接收情况21/48
会议分布
ICLR
32
NeurIPS
13
ICML
3

发表论文 (48 篇)

202523

4.5
4

A Unified Theory of Stochastic Proximal Point Methods without Smoothness

ICLR 2025Rejected
6.8
4

Local Curvature Descent: Squeezing More Curvature out of Standard and Polyak Gradient Descent

NeurIPS 2025Poster
4.3
4

Local Curvature Descent: Squeezing More Curvature out of Standard and Polyak Gradient Descent

ICLR 2025Rejected
5.8
4

On the Convergence of FedProx with Extrapolation and Inexact Prox

ICLR 2025Rejected
4.8
4

Error Feedback for Smooth and Nonsmooth Convex Optimization with Constant, Decreasing and Polyak Stepsizes

ICLR 2025Rejected
7.3
4

Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits

NeurIPS 2025Poster
6.1
4

ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning

ICML 2025Poster
4.9
4

Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity

ICML 2025Poster
7.5
4

LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression

ICLR 2025Spotlight
5.5
4

Smoothed Normalization for Efficient Distributed Private Optimization

ICML 2025Rejected
4.0
4

MindFlayer: Efficient Asynchronous Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times

ICLR 2025Rejected
4.5
4

Variance Reduced Distributed Non-Convex Optimization Using Matrix Stepsizes

ICLR 2025Rejected
7.0
4

MAST: model-agnostic sparsified training

ICLR 2025Poster
3.0
3

FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models

ICLR 2025withdrawn
4.2
5

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

ICLR 2025withdrawn
4.7
3

Tighter Performance Theory of FedExProx

ICLR 2025Rejected
3.4
5

Cohort Squeeze: Beyond a Single Communication Round per Cohort in Cross-Device Federated Learning

ICLR 2025withdrawn
5.8
4

Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy

ICLR 2025Rejected
6.2
5

Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity

ICLR 2025Poster
5.0
4

Communication-efficient Algorithms Under Generalized Smoothness Assumptions

ICLR 2025Rejected
8.2
4

Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum

NeurIPS 2025Poster
7.0
4

Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization

ICLR 2025Poster
5.0
4

RAC-LoRA: A Theoretical Optimization Framework for Low-Rank Adaptation

ICLR 2025Rejected

202425

5.8
4

Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants

ICLR 2024Poster
6.3
4

Error Feedback Shines when Features are Rare

ICLR 2024Rejected
4.8
5

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences

NeurIPS 2024Poster
5.3
4

Towards a Better Theoretical Understanding of Independent Subnetwork Training

ICLR 2024Rejected
5.8
4

On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization

NeurIPS 2024Poster
4.7
3

Improving Accelerated Federated Learning with Compression and Importance Sampling

ICLR 2024Rejected
6.3
4

Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity

NeurIPS 2024Spotlight
5.7
3

The Power of Extrapolation in Federated Learning

NeurIPS 2024Poster
5.7
3

LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression

NeurIPS 2024Rejected
6.3
4

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

NeurIPS 2024Poster
4.7
3

Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences

ICLR 2024Rejected
6.0
2

Provably Doubly Accelerated Federated Learning: The First Theoretically Successful Combination of Local Training and Communication Compression

ICLR 2024Rejected
-

MARINA Meets Matrix Stepsizes: Variance Reduced Distributed Non-Convex Optimization

ICLR 2024Rejected
5.8
4

GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity

ICLR 2024Rejected
6.0
6

FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity

ICLR 2024Poster
4.0
3

Explicit Personalization and Local Training: Double Communication Acceleration in Federated Learning

ICLR 2024Rejected
5.0
3

Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization

ICLR 2024Poster
6.3
4

Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity

NeurIPS 2024Poster
-

Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates

ICLR 2024Rejected
5.3
3

Clip21: Error Feedback for Gradient Clipping

ICLR 2024Rejected
5.0
5

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence

NeurIPS 2024Poster
5.5
4

Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences

NeurIPS 2024Poster
5.8
4

Federated Optimization Algorithms with Random Reshuffling and Gradient Compression

ICLR 2024Rejected
5.0
3

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise

ICLR 2024Rejected
5.6
5

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression

NeurIPS 2024Oral