English
Related papers

Related papers: The Effect of Batch Size on Contrastive Self-Super…

200 papers

Existing research shows that the batch size can seriously affect the performance of stochastic gradient descent~(SGD) based learning, including training speed and generalization ability. A larger batch size typically results in less…

Machine Learning · Statistics 2020-02-28 Shen-Yi Zhao , Yin-Peng Xie , Wu-Jun Li

Self-supervised learning enables the training of large neural models without the need for large, labeled datasets. It has been generating breakthroughs in several fields, including computer vision, natural language processing, biology, and…

Computation and Language · Computer Science 2023-12-19 Luis Lugo , Valentin Vielzeuf

In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data parallelism seem to differ…

Machine Learning · Computer Science 2018-12-18 Sam McCandlish , Jared Kaplan , Dario Amodei , OpenAI Dota Team

This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-11 Aswin Sivaraman , Minje Kim

Self-supervised learning (SSL) has transformed speech processing, yet its reliance on massive pre-training datasets remains a bottleneck. While robustness is often attributed to scale and diversity, the role of the data distribution is less…

Sound · Computer Science 2026-04-24 Ryan Whetten , Titouan Parcollet , Marco Dinarelli , Yannick Estève

Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minutes of labeled data. However, these systems are…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-02 Lasse Borgholt , Tycho Max Sylvester Tax , Jakob Drachmann Havtorn , Lars Maaløe , Christian Igel

Despite their impressive success, training foundation models remains computationally costly. This paper investigates how to efficiently train speech foundation models with self-supervised learning (SSL) under a limited compute budget. We…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-06 Andy T. Liu , Yi-Cheng Lin , Haibin Wu , Stefan Winkler , Hung-yi Lee

Having a sufficient quantity of quality data is a critical enabler of training effective machine learning models. Being able to effectively determine the adequacy of a dataset prior to training and evaluating a model's performance would be…

Machine Learning · Computer Science 2026-04-28 Arya Hatamian , Lionel Levine , Haniyeh Ehsani Oskouie , Majid Sarrafzadeh

The batch size is an essential parameter to tune during the development of new neural networks. Amongst other quality indicators, it has a large degree of influence on the model's accuracy, generalisability, training times and…

Machine Learning · Computer Science 2023-07-24 Tim Yarally , Luís Cruz , Daniel Feitosa , June Sallou , Arie van Deursen

Despite their wide adoption, the underlying training and memorization dynamics of very large language models is not well understood. We empirically study exact memorization in causal and masked language modeling, across model sizes and…

Computation and Language · Computer Science 2022-11-04 Kushal Tirumala , Aram H. Markosyan , Luke Zettlemoyer , Armen Aghajanyan

Finding the optimal learning rate for language model pretraining is a challenging task. This is not only because there is a complicated correlation between learning rate, batch size, number of training tokens, model size, and other…

Computation and Language · Computer Science 2024-09-13 Yikang Shen , Matthew Stallone , Mayank Mishra , Gaoyuan Zhang , Shawn Tan , Aditya Prasad , Adriana Meza Soria , David D. Cox , Rameswar Panda

Several studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the size of the dataset on which the model is fine-tuned. In this…

Computation and Language · Computer Science 2022-03-21 Houman Mehrafarin , Sara Rajaee , Mohammad Taher Pilehvar

In recent years, self-supervised contrastive learning has emerged as a distinguished paradigm in the artificial intelligence landscape. It facilitates unsupervised feature learning through contrastive delineations at the instance level.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Jiansong Zhang , Linlin Shen , Peizhong Liu

Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger. How do language models of different sizes learn during pre-training? Why do larger…

Computation and Language · Computer Science 2023-05-31 Mengzhou Xia , Mikel Artetxe , Chunting Zhou , Xi Victoria Lin , Ramakanth Pasunuru , Danqi Chen , Luke Zettlemoyer , Ves Stoyanov

Language identification greatly impacts the success of downstream tasks such as automatic speech recognition. Recently, self-supervised speech representations learned by wav2vec 2.0 have been shown to be very effective for a range of speech…

Computation and Language · Computer Science 2021-10-19 Andros Tjandra , Diptanu Gon Choudhury , Frank Zhang , Kritika Singh , Alexis Conneau , Alexei Baevski , Assaf Sela , Yatharth Saraf , Michael Auli

Conventional wisdom dictates that small batch sizes make language model pretraining and fine-tuning unstable, motivating gradient accumulation, which trades off the number of optimizer steps for a proportional increase in batch size. While…

Machine Learning · Computer Science 2025-12-17 Martin Marek , Sanae Lotfi , Aditya Somasundaram , Andrew Gordon Wilson , Micah Goldblum

Recent advances in language modeling have led to computationally intensive and resource-demanding state-of-the-art models. In an effort towards sustainable practices, we study the impact of pre-training data volume on compact language…

Computation and Language · Computer Science 2020-10-12 Vincent Micheli , Martin d'Hoffschmidt , François Fleuret

We explore the impact of pre-training data composition on the performance of small language models in a sample-efficient setting. Using datasets limited to 10 million words, we evaluate several dataset sources, including child-directed…

Computation and Language · Computer Science 2024-11-12 Hong Meng Yam , Nathan J Paek

In the development of neural text-to-speech systems, model pre-training with a large amount of non-target speakers' data is a common approach. However, in terms of ultimately achieved system performance for target speaker(s), the actual…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-11 Guangyan Zhang , Yichong Leng , Daxin Tan , Ying Qin , Kaitao Song , Xu Tan , Sheng Zhao , Tan Lee

Modern deep neural network training is typically based on mini-batch stochastic gradient optimization. While the use of large mini-batches increases the available computational parallelism, small batch training has been shown to provide…

Machine Learning · Computer Science 2018-04-23 Dominic Masters , Carlo Luschi