39 citations · 65 across the 15 of their papers we have counts for
17 papers
Personalized Federated Reinforcement Learning via Model-Agnostic Meta-Learning: Convergence of Exact and Hessian-Free Meta-Policy Gradients
Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon
We study personalized federated reinforcement learning, in which agents, each acting in its own Markov decision process, collaborate through a server to learn a shared MAML-sty…
First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
Egor Shulgin, Grigory Malinovsky, Sarit Khirirat +1
Federated Learning (FL) enables collaborative training on decentralized data. Differential privacy (DP) is crucial for FL, but current private methods often rely on unrealistic ass…
Better LMO-based Momentum Methods with Second-Order Information
Sarit Khirirat, Abdurakhmon Sadiev, Yury Demidovich +1
The use of momentum in stochastic optimization algorithms has shown empirical success across a range of machine learning tasks. Recently, a new class of stochastic momentum algorit…
Improved Convergence in Parameter-Agnostic Error Feedback through Momentum
Abdurakhmon Sadiev, Yury Demidovich, Igor Sokolov +3
Communication compression is essential for scalable distributed training of modern machine learning models, but it often degrades convergence due to the noise it introduces. Error…
Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis
Ali Beikmohammadi, Sarit Khirirat, Peter Richtárik +1
Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents. However, many existing FedR…
Smoothed Normalization for Efficient Distributed Private Optimization
Egor Shulgin, Sarit Khirirat, Peter Richtárik
Federated learning enables training machine learning models while preserving the privacy of participants. Surprisingly, there is no differentially private distributed method for sm…
Error Feedback under -Smoothness: Normalization and Momentum
Sarit Khirirat, Abdurakhmon Sadiev, Artem Riabinin +2
We provide the first proof of convergence for normalized error feedback algorithms across a wide range of machine learning problems. Despite their popularity and efficiency in trai…
Compressed Federated Reinforcement Learning with a Generative Model
Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon
Reinforcement learning has recently gained unprecedented popularity, yet it still grapples with sample inefficiency. Addressing this challenge, federated reinforcement learning (Fe…
On the Convergence of Federated Learning Algorithms without Data Similarity
Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon
Data similarity assumptions have traditionally been relied upon to understand the convergence behaviors of federated learning methods. Unfortunately, this approach often demands fi…
Parallel Momentum Methods Under Biased Gradient Estimations
Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon
Parallel stochastic gradient methods are gaining prominence in solving large-scale machine learning problems that involve data distributed across multiple nodes. However, obtaining…
Clip21: Error Feedback for Gradient Clipping
Sarit Khirirat, Eduard Gorbunov, Samuel Horváth +3
Motivated by the increasing popularity and importance of large-scale training under differential privacy (DP) constraints, we study distributed gradient methods with gradient clipp…
Balancing Privacy and Performance for Private Federated Learning Algorithms
Xiangjian Hou, Sarit Khirirat, Mohammad Yaqub +1
Federated learning (FL) is a distributed machine learning (ML) framework where multiple clients collaborate to train a model without exposing their private data. FL involves cycles…
Zeroth-Order Randomized Subspace Newton Methods
Erik Berglund, Sarit Khirirat, Xiaoyu Wang
Zeroth-order methods have become important tools for solving problems where we have access only to function evaluations. However, the zeroth-order methods only using gradient appro…
A flexible framework for communication-efficient machine learning: from HPC to IoT
Sarit Khirirat, Sindri Magnússon, Arda Aytekin +1
With the increasing scale of machine learning tasks, it has become essential to reduce the communication between computing nodes. Early work on gradient compression focused on the…
Compressed Gradient Methods with Hessian-Aided Error Compensation
Sarit Khirirat, Sindri Magnússon, Mikael Johansson
The emergence of big data has caused a dramatic shift in the operating regime for optimization algorithms. The performance bottleneck, which used to be computations, is now often c…
The Convergence of Sparsified Gradient Methods
Dan Alistarh, Torsten Hoefler, Mikael Johansson +3
Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace. Several families of comm…
Distributed learning with compressed gradients
Sarit Khirirat, Hamid Reza Feyzmahdavian, Mikael Johansson
Asynchronous computation and gradient compression have emerged as two key techniques for achieving scalability in distributed optimization for large-scale machine learning. This pa…