English
Related papers

Related papers: REMEDI: Corrective Transformations for Improved Ne…

200 papers

Most of the existing classification methods are aimed at minimization of empirical risk (through some simple point-based error measured with loss function) with added regularization. We propose to approach this problem in a more information…

Machine Learning · Computer Science 2015-01-22 Wojciech Marian Czarnecki , Jacek Tabor

Considering the difficulty of interpreting generative model output, there is significant current research focused on determining meaningful evaluation metrics. Several recent approaches utilize "precision" and "recall," borrowed from the…

Machine Learning · Computer Science 2025-02-28 Alexis Fox , Samarth Swarup , Abhijin Adiga

Predicting future vehicle purchases among existing owners presents a critical challenge due to extreme class imbalance (<0.5% positive rate) and complex behavioral patterns. We propose REMEDI (Relative feature Enhanced Meta-learning with…

Machine Learning · Computer Science 2025-05-13 Fei Liu , Huanhuan Ren , Yu Guan , Xiuxu Wang , Wang Lv , Zhiqiang Hu , Yaxi Chen

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Mackenzie J. Meni , Ryan T. White , Michael Mayo , Kevin Pilkiewicz

The major problem in information theoretic analysis of neural responses and other biological data is the reliable estimation of entropy--like quantities from small samples. We apply a recently introduced Bayesian entropy estimator to…

Data Analysis, Statistics and Probability · Physics 2009-09-29 Ilya Nemenman , William Bialek , Rob de Ruyter van Steveninck

Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the…

Machine Learning · Computer Science 2019-02-05 Dahyun Kim , Jihwan Bae , Yeonsik Jo , Jonghyun Choi

We point out a limitation of the mutual information neural estimation (MINE) where the network fails to learn at the initial training phase, leading to slow convergence in the number of training iterations. To solve this problem, we propose…

Information Theory · Computer Science 2019-06-03 Chung Chan , Ali Al-Bashabsheh , Hing Pang Huang , Michael Lim , Da Sun Handason Tam , Chao Zhao

Balanced and efficient information flow is essential for optimizing language generation models. In this work, we propose Entropy-UID, a new token selection method that balances entropy and Uniform Information Density (UID) principles for…

Computation and Language · Computer Science 2025-02-21 Xinpeng Shou

Transfer entropy measures directed information flow in time series, and it has become a fundamental quantity in applications spanning neuroscience, finance, and complex systems analysis. However, existing estimation methods suffer from the…

Machine Learning · Computer Science 2026-04-10 Simon Pedro Galeano Munoz , Mustapha Bounoua , Giulio Franzese , Pietro Michiardi , Maurizio Filippone

Estimating the entropy of a discrete random variable is a fundamental problem in information theory and related fields. This problem has many applications in various domains, including machine learning, statistics and data compression. Over…

Information Theory · Computer Science 2020-12-22 Yuval Shalev , Amichai Painsky , Irad Ben-Gal

Recently, information theoretic analysis has become a popular framework for understanding the generalization behavior of deep neural networks. It allows a direct analysis for stochastic gradient/Langevin descent (SGD/SGLD) learning…

Machine Learning · Statistics 2023-05-03 Yuxin Dong , Tieliang Gong , Hong Chen , Chen Li

A large-scale knowledge graph enhances reproducibility in biomedical data discovery by providing a standardized, integrated framework that ensures consistent interpretation across diverse datasets. It improves generalizability by connecting…

Methodology · Statistics 2024-10-11 Suqi Liu , Tianxi Cai , Xiaoou Li

Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks. This leads to substantial computational overhead with limited performance gain, primarily due to redundant…

Artificial Intelligence · Computer Science 2026-01-13 Ruichu Cai , Haopeng Du , Qingwen Lin , Yutong Chen , Zijian Li , Boyan Xu

Much of the field of Machine Learning exhibits a prominent set of failure modes, including vulnerability to adversarial examples, poor out-of-distribution (OoD) detection, miscalibration, and willingness to memorize random labelings of…

Machine Learning · Computer Science 2023-07-19 Ian Fischer

The Matrix-based Renyi's entropy enables us to directly measure information quantities from given data without the costly probability density estimation of underlying distributions, thus has been widely adopted in numerous statistical…

Machine Learning · Statistics 2022-05-17 Yuxin Dong , Tieliang Gong , Shujian Yu , Chen Li

When presented with a data stream of two statistically dependent variables, predicting the future of one of the variables (the target stream) can benefit from information about both its history and the history of the other variable (the…

Machine Learning · Computer Science 2023-03-10 Damjan Kalajdzievski , Ximeng Mao , Pascal Fortier-Poisson , Guillaume Lajoie , Blake Richards

Concept Bottleneck Models (CBMs) aim to enhance interpretability by predicting human-understandable concepts as intermediates for decision-making. However, these models often face challenges in ensuring reliable concept representations,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Yuxuan Cai , Xiyu Wang , Satoshi Tsutsui , Winnie Pang , Bihan Wen

In [1] it is shown that recurrent neural networks (RNNs) can learn - in a metric entropy optimal manner - discrete time, linear time-invariant (LTI) systems. This is effected by comparing the number of bits needed to encode the…

Dynamical Systems · Mathematics 2022-11-29 Clemens Hutter , Thomas Allard , Helmut Bölcskei

Entropy Estimation is an important problem with many applications in cryptography, statistic,machine learning. Although the estimators optimal with respect to the sample complexity have beenrecently developed, there are still some…

Data Structures and Algorithms · Computer Science 2020-02-24 Maciej Skorski

Efficient approximation lies at the heart of large-scale machine learning problems. In this paper, we propose a novel, robust maximum entropy algorithm, which is capable of dealing with hundreds of moments and allows for computationally…

Machine Learning · Statistics 2019-06-05 Diego Granziol , Binxin Ru , Stefan Zohren , Xiaowen Doing , Michael Osborne , Stephen Roberts
‹ Prev 1 2 3 10 Next ›