paper-with-me

홈 › Papers

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

2024-10-30 · Baekrok Shin, Junsoo Oh, Hanseul Cho, Chulhee Yun

Warm-starting neural network training by initializing networks with previously learned weights is appealing, as practical neural networks are often deployed under a continuous influx of new data. However, it often leads to loss of plasticity, where the network loses its ability to learn new information, resulting in worse generalization than training from scratch. This occurs even under stationary data distributions, and its underlying mechanism is poorly understood. We develop a framework emulating real-world neural network training and identify noise memorization as the primary cause of plasticity loss when warm-starting on stationary data. Motivated by this, we propose Direction-Aware SHrinking (DASH), a method aiming to mitigate plasticity loss by selectively forgetting memorized noise while preserving learned features. We validate our approach on vision tasks, demonstrating improvements in test accuracy and training efficiency.

📄 PDF Abstract BibTeX arXiv:2410.23495

Code (2)

NAVER-INTEL-Co-Lab/gaudi-dash 공식 구현 pytorch
baekrok/DASH-Direction-Aware-SHrinking 공식 구현 pytorch

Tasks

Memorization

Similar Papers 제목 키워드 기반

Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization

2026-01-14 · Rongzheng Wang, Yihong Huang, Muquan Li, Jiakai Li 외 arxiv

Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated heuristic generation. Instead of relying on manual design, this LLM-Driven Heuristic Design (LHD) process leverages LLM…

[Re] Warm-Starting Neural Network Training

2021-01-31 · RC 2020 · Amirkeivan Mohtashami, Ehsan Pajouheshgar, Klim Kireev

Scope of Reproducibility We reproduce the results of the paper ”On Warm-Starting Neural Network Training.” In many real-world applications, the training data is not readily available and is accumulated over time. As tr…

Data Augmentation

What Can Grokking Teach Us About Learning Under Nonstationarity?

2025-07-26 · Clare Lyle, Gharda Sokar, Razvan Pascanu, Andras Gyorgy arxiv

In continual learning problems, it is often necessary to overwrite components of a neural network's learned representation in response to changes in the data stream; however, neural networks often exhibit \primacy bias, …

Reinforcement LearningContinual Learning

Warmstarting for Scaling Language Models

2024-11-11 · Neeratyoy Mallik, Maciej Janowski, Johannes Hog, Herilalaina Rakotoarison 외

Scaling model sizes to scale performance has worked remarkably well for the current large language models paradigm. The research and empirical findings of various scaling studies led to novel scaling results and laws tha…

Step Out and Seek Around: On Warm-Start Training with Incremental Data

2024-06-06 · Maying Shen, Hongxu Yin, Pavlo Molchanov, Lei Mao 외

Data often arrives in sequence over time in real-world deep learning applications such as autonomous driving. When new training data is available, training the model from scratch undermines the benefit of leveraging the …

Autonomous DrivingKnowledge DistillationTransfer Learning