English
Related papers

Related papers: LCA: Loss Change Allocation for Neural Network Tra…

200 papers

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process,…

In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective. However, in many scenarios, several distinct yet correlated objectives or tasks often…

Machine Learning · Computer Science 2024-04-15 Wei Cui , Wei Yu

Behavior of neural networks is irremediably determined by the specific loss and data used during training. However it is often desirable to tune the model at inference time based on external factors such as preferences of the user or…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Matteo Maggioni , Thomas Tanay , Francesca Babiloni , Steven McDonagh , Aleš Leonardis

Comparing learned neural representations in neural networks is a challenging but important problem, which has been approached in different ways. The Centered Kernel Alignment (CKA) similarity metric, particularly its linear variant, has…

Machine Learning · Computer Science 2022-11-17 MohammadReza Davari , Stefan Horoi , Amine Natik , Guillaume Lajoie , Guy Wolf , Eugene Belilovsky

Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily…

Machine Learning · Computer Science 2023-08-15 Quanziang Wang , Renzhen Wang , Yichen Wu , Xixi Jia , Deyu Meng

Loss of trainability refers to a phenomenon in continual learning where parameter updates no longer make progress on the optimization objective, so accuracy stalls or degrades as the learning problem changes over time. In this paper, we…

Machine Learning · Computer Science 2025-12-11 Gunbir Singh Baveja , Alex Lewandowski , Mark Schmidt

Continual learning (CL) has spurred the development of several methods aimed at consolidating previous knowledge across sequential learning. Yet, the evaluations of these methods have primarily focused on the final output, such as changes…

Machine Learning · Computer Science 2024-08-20 Nishant Suresh Aswani , Amira Guesmi , Muhammad Abdullah Hanif , Muhammad Shafique

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to…

Machine Learning · Computer Science 2019-05-16 Chen Huang , Shuangfei Zhai , Walter Talbott , Miguel Angel Bautista , Shih-Yu Sun , Carlos Guestrin , Josh Susskind

Neural networks are typically trained with a single learning rate across all layers. While recent empirical evidence suggests that assigning layer-specific learning rates can accelerate training, a principled understanding of the conditions…

Machine Learning · Computer Science 2026-05-26 Sihan Zeng , Sujay Bhatt , Sumitra Ganesh

Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require thousands or millions of observations in order to solve even…

Machine Learning · Computer Science 2025-05-08 Christian Raymond

We present observations and discussion of previously unreported phenomena discovered while training residual networks. The goal of this work is to better understand the nature of neural networks through the examination of these new…

Machine Learning · Computer Science 2017-02-15 Leslie N. Smith , Nicholay Topin

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…

Surgical learning curves are graphical tools used to evaluate a trainee's progress in the early stages of their career and determine whether they have achieved proficiency after completing a specified number of surgeries. Cumulative sum…

Methodology · Statistics 2025-01-22 Adel Ahmadi Nadi , Stefan Steiner , Nathaniel Stevens

Through theoretical and experimental validation, unlike all existing adaptive methods like Adam which penalize frequently-changing parameters and are only applicable to sparse gradients, we propose the simplest SGD enhanced method,…

Machine Learning · Computer Science 2023-10-04 Gongyue Zhang , Dinghuang Zhang , Shuwen Zhao , Donghan Liu , Carrie M. Toptan , Honghai Liu

Training large models ranging from millions to billions of parameters is highly resource-intensive, requiring significant time, compute, and memory. It is observed that most of the learning (higher change in weights) takes place in the…

Machine Learning · Computer Science 2026-03-16 Krishu K Thapa , Reet Barik , Krishna Teja Chitty-Venkata , Murali Emani , Venkatram Vishwanath

Recent work has sought to understand the behavior of neural networks by comparing representations between layers and between different trained models. We examine methods for comparing neural network representations based on canonical…

Machine Learning · Computer Science 2019-07-22 Simon Kornblith , Mohammad Norouzi , Honglak Lee , Geoffrey Hinton

Loss explosions in training deep neural networks can nullify multi-million dollar training runs. Conventional monitoring metrics like weight and gradient norms are often lagging and ambiguous predictors, as their values vary dramatically…

Machine Learning · Computer Science 2025-10-07 Haiquan Qiu , You Wu , Yingjie Tan , Yaqing Wang , Quanming Yao

This paper proposes a new family of algorithms for training neural networks (NNs). These are based on recent developments in the field of non-convex optimization, going under the general name of successive convex approximation (SCA)…

Machine Learning · Statistics 2017-06-16 Simone Scardapane , Paolo Di Lorenzo

Robust principal component analysis (RPCA) is a critical tool in modern machine learning, which detects outliers in the task of low-rank matrix reconstruction. In this paper, we propose a scalable and learnable non-convex approach for…

Machine Learning · Computer Science 2023-02-28 HanQin Cai , Jialin Liu , Wotao Yin

Principal component analysis (PCA) is a well-known linear dimension-reduction method that has been widely used in data analysis and modeling. It is an unsupervised learning technique that identifies a suitable linear subspace for the input…

Machine Learning · Statistics 2021-09-10 Shaojie Xu , Joel Vaughan , Jie Chen , Agus Sudjianto , Vijayan Nair