On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

26 results for “Byzantine-robustness”

Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcs.LG

New bucketing scheme improves Byzantine robustness for heterogeneous data.

problem Byzantine attacks on federated learning with heterogeneous data.

method Bucketing scheme to adapt robust algorithms to non-iid data.

result Bucketing scheme ensures convergence against Byzantine attacks.

Byzantine robustness federated learning heterogeneous data bucketing convergence

2020-06-16abs ↗pdf ↗

Learning from History for Byzantine Robust Optimizationcs.LG

New methods improve Byzantine robustness in distributed learning.

problem Existing robust aggregation rules fail in realistic scenarios.

method Introducing new robust iterative clipping procedure and worker momentum.

result First provably robust method for standard stochastic optimization.

Byzantine robustness distributed learning federated learning aggregation rules iterative clipping

2020-12-18abs ↗pdf ↗

Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustnesscs.LG

New findings show privacy affects generalization error in a non-monotonic way.

problem Privacy and robustness in distributed learning.

method Theoretical analysis and matching lower/upper bounds on algorithmic stability.

result Generalization error is non-monotonically affected by privacy, depending on noise level.

Privacy Generalization Byzantine Robustness Distributed Learning Algorithmic Stability

2026-07-01abs ↗pdf ↗

Secure Byzantine-Robust Machine Learningcs.LG

Paper proposes a secure protocol for federated learning.

problem Combining robustness, privacy, and security in federated learning.

method Secure two-server protocol for federated learning.

result Offers both input privacy and Byzantine-robustness.

federated learning security privacy Byzantine-robustness

2020-06-08abs ↗pdf ↗

Byzantine-Robust Online and Offline Distributed Reinforcement Learningcs.LG

New algorithm identifies near-optimal policies in adversarial distributed RL settings.

problem Adversarial agents in distributed RL settings that can collude and report arbitrary data.

method Weighted-Clique algorithm for robust mean estimation from batches, combined with novel distributed algorithms.

result Achieves superior robustness guarantees and near-optimal sample complexities in both offline and online settings.

Byzantine robustness Distributed RL Reinforcement Learning Adversarial Agents Robust Estimation

2022-06-01abs ↗pdf ↗

Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescs.LG

New federated learning protocols resist Byzantine failures and offer privacy guarantees.

problem Resisting Byzantine failures in federated learning.

method Proposes robust federated learning protocols with optimal statistical rates and privacy guarantees.

result Achieves nearly optimal statistical rates and tight rate in terms of all parameters for strongly convex losses.

federated learning Byzantine robustness privacy guarantees statistical rates

2022-05-24abs ↗pdf ↗

Byzantine-Robust Decentralized Learning via ClippedGossipcs.LG

New algorithm improves decentralized learning in the presence of Byzantine faults.

problem Byzantine faults in decentralized learning on arbitrary graphs.

method Proposes ClippedGossip for Byzantine-robust consensus and optimization.

result First to provably converge to a specified neighborhood of the stationary point for non-convex objectives.

Byzantine fault tolerance Decentralized learning Consensus Optimization ClippedGossip

2022-02-03abs ↗pdf ↗

Towards Federated Learning With Byzantine-Robust Client Weightingcs.LG

A new method balances model quality and Byzantine robustness in Federated Learning.

problem Byzantine clients sending arbitrary or malicious information.

method Practical weight-truncation-based preprocessing method.

result Empirically demonstrates good balance between model quality and Byzantine robustness.

Federated Learning Byzantine Robustness Weight Truncation Machine Learning

2020-04-10abs ↗pdf ↗

Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inferencestat.ML

Paper improves statistical efficiency of median-of-means estimator for Byzantine robust distributed inference.

problem Byzantine robustness in distributed learning systems.

method Variance reduced median-of-means (VRMOM) estimator for Byzantine robust distributed inference.

result Achieves a fast convergence rate with only a constant number of rounds of communications.

Byzantine robustness median-of-means distributed inference statistical efficiency variance reduction

2021-03-04abs ↗pdf ↗

Unified Breakdown Analysis for Byzantine Robust Gossipmath.OC

Unified framework for Byzantine robust gossip algorithms with guaranteed performance.

problem Vulnerability of decentralized machine learning to misbehaving devices.

method Introduces F-RG framework and CS+ robust aggregation rule for Byzantine resilience.

result CS+-RG has near-optimal breakdown tolerance and outperforms existing methods.

Byzantine robustness Decentralized learning Gossip algorithms Robust aggregation Breakdown point

2024-10-14abs ↗pdf ↗

On the Optimal Batch Size for Byzantine-Robust Distributed Learningcs.LG

New method improves model accuracy in Byzantine-robust distributed learning by optimizing batch size.

problem Reduces model accuracy drop due to large variance of stochastic gradients in Byzantine-robust distributed learning.

method Proposes ByzSGDnm, a novel BRDL method that uses normalized momentum to mitigate accuracy drop in large batch sizes.

result The optimal batch size increases with the fraction of Byzantine workers, leading to better model accuracy under Byzantine attacks.

Byzantine-robust distributed learning optimal batch size stochastic gradient descent normalized momentum model accuracy

2023-05-23abs ↗pdf ↗

Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workerscs.LG

DynBRO learns robustly from dynamic Byzantine workers.

problem Fault-tolerant distributed learning with dynamic Byzantine workers.

method Multi-level Monte Carlo (MLMC) gradient estimation and adaptive learning rate.

result DynaBRO nearly matches static setting's convergence rate with

\mathcal{O}(\sqrt{T})

Byzantine worker changes.

Byzantine robustness dynamic workers Monte Carlo adaptive learning convergence rate

2024-02-05abs ↗pdf ↗

Byzantine-Robust Gossip: Insights from a Dual Approachcs.LG

Paper develops Byzantine-resilient algorithms for decentralized learning.

problem Vulnerability of distributed learning to Byzantine attacks.

method Dual approach for decentralized optimization.

result Convergence guarantees and experimental validation of the proposed algorithm.

Byzantine attacks Decentralized learning Dual optimization Peer-to-peer communication

2024-05-06abs ↗pdf ↗

BROADCAST: Reducing Both Stochastic and Compression Noise to Robustify Communication-Efficient Federated Learningcs.LG

Proposes a method to improve Byzantine-robustness in compressed federated learning.

problem Byzantine-robustness in compressed federated learning.

method Gradient difference compression and stochastic average gradient algorithm (SAGA).

result The proposed method reaches a neighborhood of the optimal solution at a linear convergence rate.

federated learning compression noise Byzantine attacks gradient difference stochastic average gradient

2021-04-14abs ↗pdf ↗

Communication-efficient Byzantine-robust distributed learning with statistical guaranteestat.ML

Paper develops efficient algorithms for robust distributed learning with statistical guarantees.

problem Limited communication power and adversarial node behaviors in distributed learning.

method Surrogate likelihood framework and median/trimmed mean operations.

result Provable robustness against Byzantine failures and optimal statistical rates.

distributed learning Byzantine robustness communication efficiency statistical guarantees

2021-02-28abs ↗pdf ↗

Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneitycs.LG

A new Federated Learning approach balances personalization and global training.

problem Breaking the curse of data heterogeneity in Federated Learning.

method Splitting variables into global and local parameters, using a simple algorithm.

result The approach allows each client to fit their data perfectly, breaking the curse of data heterogeneity.

Federated Learning Personalization Data Heterogeneity Global Training Asynchronous Training

2023-05-29abs ↗pdf ↗

Stochastic Alternating Direction Method of Multipliers for Byzantine-Robust Distributed Learningmath.OC

Paper tackles Byzantine attacks in distributed learning with a new ADMM method.

problem Byzantine workers sending arbitrary messages bias distributed learning.

method Byzantine-robust stochastic ADMM exploiting separable problem structure.

result Proposed method converges to optimal solution at O(1/k) rate.

Byzantine attacks distributed learning ADMM stochastic optimization convergence rate

2021-06-13abs ↗pdf ↗

Byzantine-Robust Decentralized Stochastic Optimization over Static and Time-Varying Networksmath.OC

Paper addresses Byzantine attacks in decentralized optimization over networks.

problem Byzantine attacks in decentralized stochastic optimization over static and time-varying networks.

method Formulate a TV norm-penalized approximation of the problem, solve using stochastic subgradient method.

result Proposed method reaches a neighborhood of the Byzantine-free optimal solution.

Byzantine attacks decentralized optimization stochastic subgradient total variation norm networks

2020-05-12abs ↗pdf ↗

Byzantine-Robust Clustered Federated Learningstat.ML

Paper tackles Byzantine attacks in Federated Learning by clustering and robustifying.

problem Adversarial attacks from Byzantine machines in Federated Learning.

method Iterative Federated Clustering Algorithm (IFCA) with trimmed mean and median aggregation.

result Improved convergence rate for strongly convex loss functions in Byzantine-Robust IFCA.

Federated Learning Byzantine Attacks Clustered Federated Learning Robust Clustering Trimmed Mean

2023-06-01abs ↗pdf ↗

Byzantine-Robust Variance-Reduced Federated Learning over Distributed Non-i.i.d. Datacs.LG

A method to robustly federate learning with non-i.i.d. data and Byzantine workers.

problem Byzantine workers sending malicious messages in federated learning with non-i.i.d. data.

method Resampling strategy to reduce inner and outer variation, stochastic average gradient, robust geometric median aggregation.

result The method reaches a neighborhood of the optimal solution at a linear convergence rate and learning error depends on the number of Byzantine workers.

federated learning non-i.i.d. data Byzantine workers resampling stochastic gradient

2020-09-17abs ↗pdf ↗

Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learningcs.LG

We study robust distributed learning that involves minimizing a non-convex loss function with saddle points. We consider the Byzantine setting where some worker machines have abnormal or even arbitrary and adversarial behavior. In this setting, the Byzantine machines may create fake local minima near a saddle point tha…

2018-06-14abs ↗pdf ↗

Byzantine-Robust Federated Linear Banditscs.LG

Paper addresses robust federated linear bandits against Byzantine attacks.

problem Byzantine attacks on a small fraction of agents in federated learning.

method Proposes a geometric median-based robust aggregation oracle.

result Achieves sublinear regret bound of

ilde{\mathcal{O}}({T^{3/4}})

robust to fewer than half Byzantine agents.

federated learning linear bandits Byzantine attacks robust aggregation geometric median

2022-04-03abs ↗pdf ↗

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescs.LG

In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithm…

2018-03-05abs ↗pdf ↗

Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingstat.ML

Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learning techniques are vulnerable to Byzantine failures, biased local datasets, and poisoning attacks. In this paper we introduce Adaptive Federa…

2019-09-11abs ↗pdf ↗

Communication-Efficient and Byzantine-Robust Distributed Learning with Error Feedbackcs.LG

We develop a communication-efficient distributed learning algorithm that is robust against Byzantine worker machines. We propose and analyze a distributed gradient-descent algorithm that performs a simple thresholding based on gradient norms to mitigate Byzantine failures. We show the (statistical) error-rate of our al…

2019-11-21abs ↗pdf ↗

Robust Federated Learning in a Heterogeneous Environmentcs.LG

We study a recently proposed large-scale distributed learning paradigm, namely Federated Learning, where the worker machines are end users' own devices. Statistical and computational challenges arise in Federated Learning particularly in the presence of heterogeneous data distribution (i.e., data points on different de…

2019-06-16abs ↗pdf ↗