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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “stability-plasticity”

EILearn: Learning Incrementally Using Previous Knowledge Obtained From an Ensemble of Classifierscs.LG

EILearn learns incrementally using previous classifier knowledge.

problem Incremental learning with previous data.

method Retains and uses previous classifier knowledge, monitors performance, eliminates poorly performing classifiers.

result Outperforms existing incremental learning approaches.

incremental learning ensemble classifiers previous knowledge stability-plasticity

2019-02-08abs ↗pdf ↗

Adaptive Aggregation Networks for Class-Incremental Learningcs.CV

AANets balance stability and plasticity in CIL.

problem Stability-plasticity dilemma in class-incremental learning.

method Adaptive Aggregation Networks (AANets) with stable and plastic residual blocks.

result AANets improve performance on CIL benchmarks.

class-incremental learning stability-plasticity dilemma residual blocks aggregation networks CIFAR-100

2020-10-10abs ↗pdf ↗

Dropout as an Implicit Gating Mechanism For Continual Learningcs.LG

Dropout helps a stable network learn new tasks without forgetting old ones.

problem Catastrophic forgetting in neural networks when learning multiple tasks.

method Investigate the relationship between dropout and stability in neural networks, showing dropout acts as an implicit gating mechanism.

result Dropout stabilizes a network's learning, allowing it to learn new tasks without forgetting old ones.

dropout continual learning catastrophic forgetting neural networks stability

2020-04-24abs ↗pdf ↗

Flashbacks to Harmonize Stability and Plasticity in Continual Learningcs.LG

Flashback Learning balances model stability and plasticity in continual learning.

problem Balancing model stability and plasticity in continual learning.

method Flashback Learning (FL) uses a bidirectional regularization approach to balance stability and plasticity.

result FL improves model accuracy by up to 4.91% in Class-Incremental and 3.51% in Task-Incremental settings.

Continual Learning Stability Plasticity Regularization Bidirectional

2025-05-31abs ↗pdf ↗

Batch-level Experience Replay with Review for Continual Learningcs.LG

This paper presents a method to improve continual learning stability and plasticity.

problem Balancing learning stability and plasticity in deep learning.

method Batch-level Experience Replay with Review approach.

result Achieved 1st place in all three scenarios of the CVPR 2020 CLVision challenge.

Continual Learning Experience Replay Computer Vision Deep Learning Stability

2020-07-11abs ↗pdf ↗

Neurogenesis Deep Learningcs.NE

Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as image and audio processing - data processing domains in which humans have long held clear advantages…

2016-12-12abs ↗pdf ↗

Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Pluginscs.LG

DLC enhances distillation-based continual learning with lightweight plugins.

problem Stability-plasticity dilemma in distillation-based continual learning.

method DLC deploys lightweight residual plugins into the classifier-proximal layer of a shared feature extractor.

result Significant 8% accuracy gain on large-scale benchmarks with minimal parameter increase.

continual learning distillation classifier-proximal lightweight plugins accuracy gain

2025-12-03abs ↗pdf ↗

A continual learning survey: Defying forgetting in classification taskscs.CV

Survey tackles continual learning in classification tasks to prevent forgetting.

problem Prevent catastrophic forgetting in neural networks across multiple tasks.

method Taxonomy, stability-plasticity trade-off framework, comprehensive comparison of methods.

result Empirical evaluation of continual learning methods on various benchmarks.

continual learning catastrophic forgetting neural networks classification tasks state-of-the-art

2019-09-18abs ↗pdf ↗