English
Related papers

Related papers: The HSIC Bottleneck: Deep Learning without Back-Pr…

200 papers

We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier. In addition to the usual cross-entropy loss, we add regularization terms for…

Machine Learning · Computer Science 2021-10-27 Zifeng Wang , Tong Jian , Aria Masoomi , Stratis Ioannidis , Jennifer Dy

Recent works investigated the generalization properties in deep neural networks (DNNs) by studying the Information Bottleneck in DNNs. However, the mea- surement of the mutual information (MI) is often inaccurate due to the density…

Information Theory · Computer Science 2018-02-16 Denny Wu , Yixiu Zhao , Yao-Hung Hubert Tsai , Makoto Yamada , Ruslan Salakhutdinov

We investigate the use of a non-parametric independence measure, the Hilbert-Schmidt Independence Criterion (HSIC), as a loss-function for learning robust regression and classification models. This loss-function encourages learning models…

Machine Learning · Computer Science 2020-07-14 Daniel Greenfeld , Uri Shalit

Despite superior performance on many computer vision tasks, deep convolution neural networks are well known to be compressed on devices that have resource constraints. Most existing network pruning methods require laborious human efforts…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Xiawu Zheng , Yuexiao Ma , Teng Xi , Gang Zhang , Errui Ding , Yuchao Li , Jie Chen , Yonghong Tian , Rongrong Ji

Tackling new machine learning problems with neural networks always means optimizing numerous hyperparameters that define their structure and strongly impact their performances. In this work, we study the use of goal-oriented sensitivity…

Machine Learning · Statistics 2022-07-14 Paul Novello , Gaël Poëtte , David Lugato , Pietro Marco Congedo

We approach self-supervised learning of image representations from a statistical dependence perspective, proposing Self-Supervised Learning with the Hilbert-Schmidt Independence Criterion (SSL-HSIC). SSL-HSIC maximizes dependence between…

Machine Learning · Statistics 2021-12-06 Yazhe Li , Roman Pogodin , Danica J. Sutherland , Arthur Gretton

Rehearsal-based approaches are a mainstay of continual learning (CL). They mitigate the catastrophic forgetting problem by maintaining a small fixed-size buffer with a subset of data from past tasks. While most rehearsal-based approaches…

Machine Learning · Computer Science 2023-05-02 Zifeng Wang , Zheng Zhan , Yifan Gong , Yucai Shao , Stratis Ioannidis , Yanzhi Wang , Jennifer Dy

Many tools exist to detect dependence between random variables, a core question across a wide range of machine learning, statistical, and scientific endeavors. Although several statistical tests guarantee eventual detection of any…

Machine Learning · Statistics 2026-03-23 Nathaniel Xu , Feng Liu , Danica J. Sutherland

Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams such as continual learning. One powerful approach that has…

The information bottleneck framework provides a systematic approach to learning representations that compress nuisance information in the input and extract semantically meaningful information about predictions. However, the choice of a…

Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. However, due to…

Machine Learning · Computer Science 2017-01-17 Xi He , Dheevatsa Mudigere , Mikhail Smelyanskiy , Martin Takáč

Spiking neural networks (SNNs) are positioned to enable spatio-temporal information processing and ultra-low power event-driven neuromorphic hardware. However, SNNs are yet to reach the same performances of conventional deep artificial…

Neural and Evolutionary Computing · Computer Science 2019-01-23 Yingyezhe Jin , Wenrui Zhang , Peng Li

Deep neural networks are susceptible to catastrophic forgetting when trained on sequential tasks. Various continual learning (CL) methods often rely on exemplar buffers or/and network expansion for balancing model stability and plasticity,…

Machine Learning · Computer Science 2024-01-18 Depeng Li , Tianqi Wang , Junwei Chen , Qining Ren , Kenji Kawaguchi , Zhigang Zeng

We develop a Hilbert--Schmidt independence criterion (HSIC)-based framework for testing serial independence in strictly stationary time series. The proposed auto Hilbert--Schmidt independence criterion (AutoHSIC) measures dependence between…

Methodology · Statistics 2026-05-22 Muyi Li , Yuqing Xu , Zhou Zhou

Parameterizing the approximate posterior of a generative model with neural networks has become a common theme in recent machine learning research. While providing appealing flexibility, this approach makes it difficult to impose or assess…

Machine Learning · Computer Science 2018-11-30 Romain Lopez , Jeffrey Regier , Michael I. Jordan , Nir Yosef

This study introduces a novel supervised learning approach for spiking neural networks that does not rely on traditional backpropagation. Instead, it employs spike-timing-dependent plasticity (STDP) within a supervised framework for image…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Wei Xie

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

We present a fully memristive spiking neural network (MSNN) consisting of novel memristive neurons trained using the backpropagation through time (BPTT) learning rule. Gradient descent is applied directly to the memristive…

Neural and Evolutionary Computing · Computer Science 2022-03-11 Peng Zhou , Jason K. Eshraghian , Dong-Uk Choi , Sung-Mo Kang

The error-backpropagation (backprop) algorithm remains the most common solution to the credit assignment problem in artificial neural networks. In neuroscience, it is unclear whether the brain could adopt a similar strategy to correctly…

Neurons and Cognition · Quantitative Biology 2022-10-25 Will Greedy , Heng Wei Zhu , Joseph Pemberton , Jack Mellor , Rui Ponte Costa

Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate. The sensitivity to the learning rate is due to the reliance on backpropagation to train the network. In this paper we…

Machine Learning · Statistics 2018-08-08 Francois Fagan , Garud Iyengar
‹ Prev 1 2 3 10 Next ›