Samuel Horváth
29 papers · 2019–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (13) 🌍 Conference Polyglot (8)
🗺️
Taxonomy Completionist
(13)
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
🤝
Dynamic Duo
(13)
👑
Triple Crown
🔥
Unstoppable
(7)
💎
Century Club
(29)
⚡
Prolific Year
(8)
🗃️
Keyword Collector
(79)
Conferences
ICML (8)
NIPS (7)
AISTATS (5)
ICLR (4)
IJCAI (2)
ALT (1)
EMNLP (1)
JMLR (1)
Top co-authors
Keywords
federated learning
(8)
variance reduction
(3)
personalized federated learning
(3)
stochastic optimization
(3)
variational inequality
(3)
uncertainty quantification
(2)
data heterogeneity
(2)
convergence guarantee
(2)
non-convex optimization
(2)
distributed learning
(2)
stochastic gradient
(2)
byzantine robustness
(2)
distributed optimization
(2)
communication compression
(2)
sample efficiency
(1)
convex optimization
(1)
transfer learning
(1)
stochastic gradient descent
(1)
conformal prediction
(1)
communication complexity
(1)
Papers
Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
ICML 2025
Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks
ICML 2025
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
ICML 2025
Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
AISTATS 2025
DPFL: Decentralized Personalized Federated Learning
AISTATS 2025
Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity
ICLR 2025
Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
ICLR 2025
Efficient Conformal Prediction under Data Heterogeneity
AISTATS 2024
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise
ICML 2024
Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
ICML 2024
Redefining Contributions: Shapley-Driven Federated Learning
IJCAI 2024
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
NIPS 2024
Low-Resource Machine Translation through the Lens of Personalized Federated Learning
EMNLP 2024
Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
NIPS 2024
Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks
IJCAI 2024
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top
ICLR 2023
Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity
ICML 2023
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
ICML 2023
On Biased Compression for Distributed Learning
JMLR 2023
Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition
NIPS 2023
Byzantine-Tolerant Methods for Distributed Variational Inequalities
NIPS 2023
Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance
NIPS 2023
FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning
AISTATS 2022
A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning
ICLR 2021
FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
NIPS 2021
Hyperparameter Transfer Learning with Adaptive Complexity
AISTATS 2021
Lower Bounds and Optimal Algorithms for Personalized Federated Learning
NIPS 2020
Don’t Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop
ALT 2020
Nonconvex Variance Reduced Optimization with Arbitrary Sampling
ICML 2019