English
Related papers

Related papers: Another reason why normalized gain should continue…

200 papers

Foundational image-language models have generated considerable interest due to their efficient adaptation to downstream tasks by prompt learning. Prompt learning treats part of the language model input as trainable while freezing the rest,…

Gradient-based meta-learning has proven to be highly effective at learning model initializations, representations, and update rules that allow fast adaptation from a few samples. The core idea behind these approaches is to use fast…

Machine Learning · Computer Science 2019-10-07 Khurram Javed , Hengshuai Yao , Martha White

Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as…

Machine Learning · Statistics 2018-07-03 Henry Gouk , Bernhard Pfahringer , Eibe Frank , Michael Cree

In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as dropout, weight decay or data augmentation sometimes help, but…

Machine Learning · Computer Science 2020-11-23 Hrayr Harutyunyan , Kyle Reing , Greg Ver Steeg , Aram Galstyan

Recent studies claim that human behavior in a two-armed Bernoulli bandit (TABB) task is described by positivity and confirmation biases, implying that humans do not integrate new information objectively. However, we find that even if the…

Artificial Intelligence · Computer Science 2025-05-14 Prakhar Godara

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

Machine Learning · Computer Science 2023-01-31 Hongru Yang , Yingbin Liang , Xiaojie Guo , Lingfei Wu , Zhangyang Wang

The brain prepares for learning even before interacting with the environment, by refining and optimizing its structures through spontaneous neural activity that resembles random noise. However, the mechanism of such a process has yet to be…

Machine Learning · Computer Science 2025-05-12 Jeonghwan Cheon , Sang Wan Lee , Se-Bum Paik

Physics-informed neural networks (PINNs) have recently emerged as a prominent paradigm for solving partial differential equations (PDEs), yet their training strategies remain underexplored. While hard prioritization methods inspired by…

Machine Learning · Computer Science 2025-12-22 Zhaoqian Gao , Min Yanga

This paper introduces a novel method for optimizing learning rates in machine learning. A previously unrecognized proportionality between learning rates and dataset sizes is discovered, providing valuable insights into how dataset scale…

Machine Learning · Computer Science 2025-05-21 Nathan Faraj

Research on generalization bounds for deep networks seeks to give ways to predict test error using just the training dataset and the network parameters. While generalization bounds can give many insights about architecture design, training…

Machine Learning · Computer Science 2022-03-21 Yi Zhang , Arushi Gupta , Nikunj Saunshi , Sanjeev Arora

At an early age, human infants are able to learn and build a model of the world very quickly by constantly observing and interacting with objects around them. One of the most fundamental intuitions human infants acquire is intuitive…

Machine Learning · Computer Science 2019-07-09 JaeWon Choi , Sung-eui Yoon

Humans sometimes have an insight that leads to a sudden and drastic performance improvement on the task they are working on. Sudden strategy adaptations are often linked to insights, considered to be a unique aspect of human cognition tied…

Artificial Intelligence · Computer Science 2024-03-04 Anika T. Löwe , Léo Touzo , Paul S. Muhle-Karbe , Andrew M. Saxe , Christopher Summerfield , Nicolas W. Schuck

Recurrent neural networks (RNNs) are powerful models of sequential data. They have been successfully used in domains such as text and speech. However, RNNs are susceptible to overfitting; regularization is important. In this paper we…

Machine Learning · Statistics 2018-07-16 Adji B. Dieng , Rajesh Ranganath , Jaan Altosaar , David M. Blei

Two recently introduced criteria for estimation of generative models are both based on a reduction to binary classification. Noise-contrastive estimation (NCE) is an estimation procedure in which a generative model is trained to be able to…

Machine Learning · Statistics 2015-05-22 Ian J. Goodfellow

Denoising score matching plays a pivotal role in the performance of diffusion-based generative models. However, the empirical optimal score--the exact solution to the denoising score matching--leads to memorization, where generated samples…

Machine Learning · Statistics 2025-05-07 Yu-Han Wu , Pierre Marion , Gérard Biau , Claire Boyer

Much research in machine learning involves finding appropriate inductive biases (e.g. convolutional neural networks, momentum-based optimizers, transformers) to promote generalization on tasks. However, quantification of the amount of…

Machine Learning · Computer Science 2024-06-25 Akhilan Boopathy , William Yue , Jaedong Hwang , Abhiram Iyer , Ila Fiete

We introduce Classification with Alternating Normalization (CAN), a non-parametric post-processing step for classification. CAN improves classification accuracy for challenging examples by re-adjusting their predicted class probability…

Machine Learning · Computer Science 2021-09-29 Menglin Jia , Austin Reiter , Ser-Nam Lim , Yoav Artzi , Claire Cardie

Statistical mechanics is used to study unrealizable generalization in two large feed-forward neural networks with binary weights and output, a perceptron and a tree committee machine. The student is trained by a teacher being larger, i.e.…

Condensed Matter · Physics 2007-05-23 Matts Sporre

Most complex machine learning and modelling techniques are prone to over-fitting and may subsequently generalise poorly to future data. Artificial neural networks are no different in this regard and, despite having a level of implicit…

Machine Learning · Statistics 2022-05-26 Vincent Szolnoky , Viktor Andersson , Balazs Kulcsar , Rebecka Jörnsten

Learning reward functions from data is a promising path towards achieving scalable Reinforcement Learning (RL) for robotics. However, a major challenge in training agents from learned reward models is that the agent can learn to exploit…

Machine Learning · Computer Science 2019-11-04 Danfei Xu , Misha Denil