paper-with-me

홈 › Papers

Gradient-matching coresets for continual learning

2021-12-09 · Lukas Balles, Giovanni Zappella, Cédric Archambeau

We devise a coreset selection method based on the idea of gradient matching: The gradients induced by the coreset should match, as closely as possible, those induced by the original training dataset. We evaluate the method in the context of continual learning, where it can be used to curate a rehearsal memory. Our method performs strong competitors such as reservoir sampling across a range of memory sizes.

📄 PDF Abstract BibTeX arXiv:2112.05025

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Gradient-Matching Coresets for Rehearsal-Based Continual Learning

2022-03-28 · Lukas Balles, Giovanni Zappella, Cédric Archambeau

The goal of continual learning (CL) is to efficiently update a machine learning model with new data without forgetting previously-learned knowledge. Most widely-used CL methods rely on a rehearsal memory of data points t…

Continual LearningManagement

Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients

2019-04-24 · Yu Chen, Tom Diethe, Neil Lawrence

Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the knowledge of previous tasks while learn…

Continual LearningTask 2

Mini-batch Coresets for Memory-efficient Training of Large Language Models

2024-07-28 · Dang Nguyen, Wenhan Yang, Rathul Anand, Yu Yang 외

Training with larger mini-batches improves the convergence rate and can yield superior performance. However, training with large mini-batches becomes prohibitive for Large Language Models (LLMs), due to the large GPU mem…

GPUNetwork Pruning

Coresets via Bilevel Optimization for Continual Learning and Streaming

2020-06-06 · NeurIPS 2020 12 · Zalán Borsos, Mojmír Mutný, Andreas Krause

Coresets are small data summaries that are sufficient for model training. They can be maintained online, enabling efficient handling of large data streams under resource constraints. However, existing constructions are l…

Bilevel OptimizationContinual Learningregression

Wasserstein Measure Coresets

2018-05-18 · Sebastian Claici, Aude Genevay, Justin Solomon

The proliferation of large data sets and Bayesian inference techniques motivates demand for better data sparsification. Coresets provide a principled way of summarizing a large dataset via a smaller one that is guarantee…

Bayesian InferenceClustering