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.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “rehearsal-free”

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batchescs.LG

Paper introduces rehearsal-free continual learning for small, non-i.i.d. batches in robotic vision.

problem Learning new objects and improving recognition in a changing robotic environment.

method Two rehearsal-free continual learning techniques (CWR* and AR1*) for small, non-i.i.d. batches.

result AR1* outperforms other techniques by more than 15% in some cases.

continual learning rehearsal-free non-i.i.d. batches robotic vision object recognition

2019-07-08abs ↗pdf ↗

Class-Incremental Learning with Generative Classifierscs.LG

A new generative classification strategy outperforms existing methods in class-incremental learning.

problem Incrementally training deep neural networks to recognize new classes is challenging.

method Proposes learning the joint distribution p(x,y) and performing classification using Bayes' rule, implemented with variational autoencoders and importance sampling.

result Performs very well on continual learning benchmarks, outperforming existing baselines.

class-incremental learning generative classification variational autoencoder Bayes' rule importance sampling

2021-04-20abs ↗pdf ↗

Prediction Error-based Classification for Class-Incremental Learningcs.LG

PEC improves class-incremental learning by measuring prediction error.

problem Challenges in class-incremental learning, particularly forgetting and class imbalance.

method Prediction Error-based Classification (PEC) measures prediction error of a model trained on data from a class.

result PEC outperforms other methods in class-incremental learning across multiple benchmarks.

class-incremental learning prediction error sample efficiency Gaussian Process

2023-05-30abs ↗pdf ↗