English
Related papers

Related papers: Estimating the Local Learning Coefficient at Scale

200 papers

The Local Learning Coefficient (LLC) is introduced as a novel complexity measure for deep neural networks (DNNs). Recognizing the limitations of traditional complexity measures, the LLC leverages Singular Learning Theory (SLT), which has…

Machine Learning · Statistics 2024-10-02 Edmund Lau , Zach Furman , George Wang , Daniel Murfet , Susan Wei

We introduce refined variants of the Local Learning Coefficient (LLC), a measure of model complexity grounded in singular learning theory, to study the development of internal structure in transformer language models during training. By…

Machine Learning · Computer Science 2024-10-07 George Wang , Jesse Hoogland , Stan van Wingerden , Zach Furman , Daniel Murfet

Learning a deep model from small data is yet an opening and challenging problem. We focus on one-shot classification by deep learning approach based on a small quantity of training samples. We proposed a novel deep learning approach named…

Machine Learning · Computer Science 2018-02-13 Chuanyun Xu , Yang Zhang , Xin Feng , YongXing Ge , Yihao Zhang , Jianwu Long

For a long time, designing neural architectures that exhibit high performance was considered a dark art that required expert hand-tuning. One of the few well-known guidelines for architecture design is the avoidance of exploding gradients,…

Machine Learning · Computer Science 2021-06-10 George Philipp , Jaime G. Carbonell

We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suite with quantization,…

Machine Learning · Statistics 2025-10-15 Einar Urdshals , Edmund Lau , Jesse Hoogland , Stan van Wingerden , Daniel Murfet

Three-layer neural networks are known to form singular learning models, and their Bayesian asymptotic behavior is governed by the learning coefficient, or real log canonical threshold. Although this quantity has been clarified for regular…

Machine Learning · Computer Science 2026-03-16 Yuki Kurumadani

Learning a Bayesian network structure from data is an NP-hard problem and thus exact algorithms are feasible only for small data sets. Therefore, network structures for larger networks are usually learned with various heuristics. Another…

Machine Learning · Computer Science 2012-10-19 Teppo Niinimaki , Pekka Parviainen

To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent and robust performance across runs. Our empirical analysis…

Machine Learning · Computer Science 2026-01-05 Waqas Ahmed , Sheeba Samuel , Kevin Coakley , Birgitta Koenig-Ries , Odd Erik Gundersen

Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger…

Machine Learning · Computer Science 2025-02-20 Yifei Yang , Zouying Cao , Xinbei Ma , Yao Yao , Libo Qin , Zhi Chen , Hai Zhao

We develop a geometric account of sequence modelling that links patterns in the data to measurable properties of the loss landscape in transformer networks. First, we cast conditional sequence distributions into a Hilbert-space framework…

Machine Learning · Computer Science 2025-04-28 Zhongtian Chen , Daniel Murfet

Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, it can be desirable to train models on a continuous stream of…

Machine Learning · Computer Science 2023-09-04 Nicolas Michel , Giovanni Chierchia , Romain Negrel , Jean-François Bercher , Toshihiko Yamasaki

In-context learning (ICL) has emerged as an effective approach to enhance the performance of large language models (LLMs). However, its effectiveness varies significantly across models and tasks, posing challenges for practitioners to…

Computation and Language · Computer Science 2025-07-15 Dingzriui Wang , Xuanliang Zhang , Keyan Xu , Qingfu Zhu , Wanxiang Che , Yang Deng

In this work, a deep learning-based method for log-likelihood ratio (LLR) lossy compression and quantization is proposed, with emphasis on a single-input single-output uncorrelated fading communication setting. A deep autoencoder network is…

Machine Learning · Computer Science 2021-05-11 Marius Arvinte , Ahmed H. Tewfik , Sriram Vishwanath

Modern neural network architectures for large-scale learning tasks have substantially higher model complexities, which makes understanding, visualizing and training these architectures difficult. Recent contributions to deep learning…

Machine Learning · Computer Science 2024-10-30 Jayadeva , Himanshu Pant , Mayank Sharma , Abhimanyu Dubey , Sumit Soman , Suraj Tripathi , Sai Guruju , Nihal Goalla

Large Language Models (LLMs) have demonstrated the ability to solve complex tasks through In-Context Learning (ICL), where models learn from a few input-output pairs without explicit fine-tuning. In this paper, we explore the capacity of…

Machine Learning · Computer Science 2024-11-26 Paimon Goulart , Evangelos E. Papalexakis

Label distribution learning (LDL) is an effective method to predict the label description degree (a.k.a. label distribution) of a sample. However, annotating label distribution (LD) for training samples is extremely costly. So recent…

Machine Learning · Computer Science 2024-05-14 Yuheng Jia , Jiawei Tang , Jiahao Jiang

Large Language Models (LLMs) have the impressive ability to perform in-context learning (ICL) from only a few examples, but the success of ICL varies widely from task to task. Thus, it is important to quickly determine whether ICL is…

Computation and Language · Computer Science 2023-10-27 Harvey Yiyun Fu , Qinyuan Ye , Albert Xu , Xiang Ren , Robin Jia

Recent advances have clarified theoretical learning accuracy in Bayesian inference, revealing that the asymptotic behavior of metrics such as generalization loss and free energy, assessing predictive accuracy, is dictated by a rational…

Statistics Theory · Mathematics 2024-08-15 Yuki Kurumadani

Semi-supervised learning has received attention from researchers, as it allows one to exploit the structure of unlabeled data to achieve competitive classification results with much fewer labels than supervised approaches. The Local and…

Machine Learning · Computer Science 2022-01-11 Bruno Klaus de Aquino Afonso , Lilian Berton

Learning from Label Proportions (LLP) is a weakly supervised learning method that aims to perform instance classification from training data consisting of pairs of bags containing multiple instances and the class label proportions within…

Machine Learning · Computer Science 2023-02-22 Ryoma Kobayashi , Yusuke Mukuta , Tatsuya Harada
‹ Prev 1 2 3 10 Next ›