English
Related papers

Related papers: Dynamic learning rate using Mutual Information

200 papers

The concepts of conditional mutual information (CMI) and normalized conditional mutual information (NCMI) are introduced to measure the concentration and separation performance of a classification deep neural network (DNN) in the output…

Machine Learning · Computer Science 2023-09-19 En-Hui Yang , Shayan Mohajer Hamidi , Linfeng Ye , Renhao Tan , Beverly Yang

Estimating mutual correlations between random variables or data streams is essential for intelligent behavior and decision-making. As a fundamental quantity for measuring statistical relationships, mutual information has been extensively…

Information Theory · Computer Science 2024-02-16 Zhengyang Hu , Song Kang , Qunsong Zeng , Kaibin Huang , Yanchao Yang

Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…

Computer Vision and Pattern Recognition · Computer Science 2020-09-14 Chang-Hui Liang , Wan-Lei Zhao , Run-Qing Chen

Mutual information (MI) is a fundamental measure of statistical dependence between two variables, yet accurate estimation from finite data remains notoriously difficult. No estimator is universally reliable, and common approaches fail in…

Data Analysis, Statistics and Probability · Physics 2025-10-02 Eslam Abdelaleem , K. Michael Martini , Ilya Nemenman

The learning rate is one of the most important hyperparameters in deep learning, and how to control it is an active area within both AutoML and deep learning research. Approaches for learning rate control span from classic optimization to…

Machine Learning · Computer Science 2025-07-03 Micha Henheik , Theresa Eimer , Marius Lindauer

Although deep learning has produced dazzling successes for applications of image, speech, and video processing in the past few years, most trainings are with suboptimal hyper-parameters, requiring unnecessarily long training times. Setting…

Machine Learning · Computer Science 2018-04-25 Leslie N. Smith

In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about…

Mutual information (MI) is a general measure of statistical dependence with widespread application across the sciences. However, estimating MI between multi-dimensional variables is challenging because the number of samples necessary to…

Quantitative Methods · Quantitative Biology 2025-03-06 Gokul Gowri , Xiao-Kang Lun , Allon M. Klein , Peng Yin

In deep Reinforcement Learning (RL), the learning rate critically influences both stability and performance, yet its optimal value shifts during training as the environment and policy evolve. Standard decay schedulers assume monotonic…

Machine Learning · Computer Science 2025-10-09 Henrique Donâncio , Antoine Barrier , Leah F. South , Florence Forbes

This paper introduces and evaluates a novel training method for neural networks: Dual Variable Learning Rates (DVLR). Building on insights from behavioral psychology, the dual learning rates are used to emphasize correct and incorrect…

Machine Learning · Computer Science 2021-02-11 Elizabeth Liner , Risto Miikkulainen

Reinforcement Learning (RL) agents deployed in real-world environments face degradation from sensor faults, actuator wear, and environmental shifts, yet lack intrinsic mechanisms to detect and diagnose these failures. We present an…

Artificial Intelligence · Computer Science 2025-09-15 Cameron Reid , Wael Hafez , Amirhossein Nazeri

It is known that the learning rate is the most important hyper-parameter to tune for training deep neural networks. This paper describes a new method for setting the learning rate, named cyclical learning rates, which practically eliminates…

Computer Vision and Pattern Recognition · Computer Science 2017-04-05 Leslie N. Smith

We propose a fully data-driven approach to designing mutual information (MI) estimators. Since any MI estimator is a function of the observed sample from two random variables, we parameterize this function with a neural network (MIST) and…

Machine Learning · Computer Science 2026-02-24 German Gritsai , Megan Richards , Maxime Méloux , Kyunghyun Cho , Maxime Peyrard

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

Transfer learning is a valuable tool in deep learning as it allows propagating information from one "source dataset" to another "target dataset", especially in the case of a small number of training examples in the latter. Yet,…

Machine Learning · Computer Science 2023-06-13 Daniel Jakubovitz , David Uliel , Miguel Rodrigues , Raja Giryes

Training neural networks can be challenging, especially as the complexity of the problem increases. Despite using wider or deeper networks, training them can be a tedious process, especially if a wrong choice of the hyperparameter is made.…

Computational Engineering, Finance, and Science · Computer Science 2025-07-30 D. Veerababu , Ashwin A. Raikar , Prasanta K. Ghosh

Dynamic feature selection, where we sequentially query features to make accurate predictions with a minimal budget, is a promising paradigm to reduce feature acquisition costs and provide transparency into a model's predictions. The problem…

Machine Learning · Computer Science 2024-09-10 Soham Gadgil , Ian Covert , Su-In Lee

The presence of mutual information in the research of deep learning has grown significantly. It has been proven that mutual information can be a good objective function to build a robust deep learning model. Most of the researches utilize…

Information Theory · Computer Science 2021-06-29 Marshal Arijona Sinaga

This work focuses on learning useful and robust deep world models using multiple, possibly unreliable, sensors. We find that current methods do not sufficiently encourage a shared representation between modalities; this can cause poor…

Machine Learning · Computer Science 2021-07-07 Kaiqi Chen , Yong Lee , Harold Soh

The ability to train randomly initialised deep neural networks is known to depend strongly on the variance of the weight matrices and biases as well as the choice of nonlinear activation. Here we complement the existing geometric analysis…

Information Theory · Computer Science 2021-02-09 Jared Tanner , Giuseppe Ughi