paper-with-me

Papers

Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing

2019-03-25 · NAACL 2019 6 · Hao Fu, Chunyuan Li, Xiaodong Liu, Jianfeng Gao, Asli Celikyilmaz, Lawrence Carin

Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. The VAE objective consists of two terms, (i) reconstruction and (ii) KL regularization, balanced by a weighting hyper-parameter \beta. One notorious training difficulty is that the KL term tends to vanish. In this paper we study scheduling schemes for \beta, and show that KL vanishing is caused by the lack of good latent codes in training the decoder at the beginning of optimization. To remedy this, we propose a cyclical annealing schedule, which repeats the process of increasing \beta multiple times. This new procedure allows the progressive learning of more meaningful latent codes, by leveraging the informative representations of previous cycles as warm re-starts. The effectiveness of cyclical annealing is validated on a broad range of NLP tasks, including language modeling, dialog response generation and unsupervised language pre-training.

📄 PDF Abstract BibTeX arXiv:1903.10145

Code (2)

haofuml/cyclical_annealing 공식 구현 tf
suvalaki/Deeper tf

Tasks

DecoderLanguage ModelingLanguage ModellingResponse GenerationScheduling

Methods 이 논문이 사용한 방법론

USD Coin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Cyclical Log Annealing as a Learning Rate Scheduler

2024-03-13 · Philip Naveen

A learning rate scheduler is a predefined set of instructions for varying search stepsizes during model training processes. This paper introduces a new logarithmic method using harsh restarting of step sizes through stoc…

Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error

2020-03-04 · Yusuke Hayashi, Taiji Suzuki

The ability to learn new concepts with small amounts of data is a crucial aspect of intelligence that has proven challenging for deep learning methods. Meta-learning for few-shot learning offers a potential solution to t…

Few-Shot LearningMeta-Learning

Parameter Re-Initialization through Cyclical Batch Size Schedules

2018-12-04 · Norman Mu, Zhewei Yao, Amir Gholami, Kurt Keutzer 외

Optimal parameter initialization remains a crucial problem for neural network training. A poor weight initialization may take longer to train and/or converge to sub-optimal solutions. Here, we propose a method of weight …

General Classificationimage-classificationImage ClassificationLanguage Modeling+2

ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding

2023-11-19 · Xuxin Cheng, Bowen Cao, Qichen Ye, Zhihong Zhu 외

Spoken language understanding (SLU) is a fundamental task in the task-oriented dialogue systems. However, the inevitable errors from automatic speech recognition (ASR) usually impair the understanding performance and lea…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Contrastive Learningspeech-recognition+3

When to restart? Exploring escalating restarts on convergence

2026-03-04 · Ayush K. Varshney, Šarūnas Girdzijauskas, Konstantinos Vandikas, Aneta Vulgarakis Feljan arxiv

Learning rate scheduling plays a critical role in the optimization of deep neural networks, directly influencing convergence speed, stability, and generalization. While existing schedulers such as cosine annealing, cycli…