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

7 results for “meta-updates”

Ultra Efficient Transfer Learning with Meta Update for Cross Subject EEG Classificationcs.LG

A new method improves EEG classification across subjects efficiently.

problem Challenges in adapting and retaining knowledge for EEG classifiers across different subjects.

method Meta UPdate Strategy (MUPS-EEG) for continuous EEG classification.

result Outperforms current state-of-the-art methods in adapting to new subjects and retaining knowledge of learned subjects.

EEG classification transfer learning meta learning cross subject deep learning

2020-03-13abs ↗pdf ↗

Bayesian Model-Agnostic Meta-Learningcs.LG

Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines scalable gradient-based meta-learning with non…

2018-06-11abs ↗pdf ↗

FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cyclingcs.LG

FedCluster accelerates federated learning convergence by cycling device groups.

problem Federated learning convergence issues with device-level data heterogeneity.

method FedCluster groups devices into clusters that cycle through learning rounds, boosting convergence with meta-updates.

result FedCluster achieves faster convergence in nonconvex optimization compared to FedAvg.

federated learning convergence cycling meta-updates device heterogeneity

2020-09-22abs ↗pdf ↗

Gradient-EM Bayesian Meta-learningcs.LG

Gradient-EM Bayesian meta-learning accelerates adaptation with reduced computation and improved robustness.

problem Efficient and robust adaptation to new tasks with uncertainty assessment.

method Extends Bayesian meta-learning with gradient-EM algorithm, decoupling inner-update from meta-update.

result Improves accuracy with less computation cost and enhanced robustness to uncertainty.

Bayesian meta-learning gradient-EM deep neural networks few-shot learning reinforcement learning

2020-06-21abs ↗pdf ↗

Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updatingcs.LG

Federated learning (FL) aims to train machine learning models in the decentralized system consisting of an enormous amount of smart edge devices. Federated averaging (FedAvg), the fundamental algorithm in FL settings, proposes on-device training and model aggregation to avoid the potential heavy communication costs and…

2019-10-18abs ↗pdf ↗

BI-MAML: Balanced Incremental Approach for Meta Learningcs.LG

BI-MAML learns multiple tasks without forgetting old ones.

problem Catastrophic forgetting in meta learning.

method Incremental model adaptation with balanced learning strategy.

result BI-MAML outperforms state-of-the-art models in accuracy and efficiency.

meta learning catastrophic forgetting incremental adaptation balanced strategy multiple tasks

2020-06-12abs ↗pdf ↗

iTAML: An Incremental Task-Agnostic Meta-learning Approachcs.LG

Meta-learning approach prevents forgetting across tasks.

problem Catastrophic forgetting in deep neural networks.

method Incremental Task-Agnostic Meta-learning (iTAML) with a meta-update rule.

result Significant improvements in class-incremental learning tasks.

meta-learning catastrophic forgetting incremental learning deep neural networks

2020-03-25abs ↗pdf ↗