English
Related papers

Related papers: GMM-Free Flat Start Sequence-Discriminative DNN Tr…

200 papers

While supervised deep learning has achieved great success in a range of applications, relatively little work has studied the discovery of knowledge from unlabeled data. In this paper, we propose an unsupervised deep learning framework to…

Computer Vision and Pattern Recognition · Computer Science 2020-09-14 Jinghua Wang , Jianmin Jiang

An intrinsic problem of classifiers based on machine learning (ML) methods is that their learning time grows as the size and complexity of the training dataset increases. For this reason, it is important to have efficient computational…

Machine Learning · Computer Science 2013-04-16 Khadoudja Ghanem

Training Artificial Neural Networks poses a challenging and critical problem in machine learning. Despite the effectiveness of gradient-based learning methods, such as Stochastic Gradient Descent (SGD), in training neural networks, they do…

Deep Learning (DL) methods show very good performance when trained on large, balanced data sets. However, many practical problems involve imbalanced data sets, or/and classes with a small number of training samples. The performance of DL…

Machine Learning · Computer Science 2017-02-07 Dolev Raviv , Margarita Osadchy

The paradigm shift from shallow classifiers with hand-crafted features to end-to-end trainable deep learning models has shown significant improvements on supervised learning tasks. Despite the promising power of deep neural networks (DNN),…

Machine Learning · Computer Science 2017-06-09 Chih-Kuan Yeh , Yao-Hung Hubert Tsai , Yu-Chiang Frank Wang

Training deep neural networks remains computationally intensive due to the itera2 tive nature of gradient-based optimization. We propose Gradient Flow Matching (GFM), a continuous-time modeling framework that treats neural network training…

Machine Learning · Computer Science 2025-05-27 Xiao Shou , Yanna Ding , Jianxi Gao

The learning of Gaussian Mixture Models (also referred to simply as GMMs) plays an important role in machine learning. Known for their expressiveness and interpretability, Gaussian mixture models have a wide range of applications, from…

Machine Learning · Computer Science 2023-07-14 Ruichong Zhang

Graph Neural Networks (GNNs) are deep-learning architectures designed for graph-type data, where understanding relationships among individual observations is crucial. However, achieving promising GNN performance, especially on unseen data,…

Machine Learning · Computer Science 2024-05-22 Lequan Lin , Dai Shi , Andi Han , Zhiyong Wang , Junbin Gao

Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-24 Sian Jin , Guanpeng Li , Shuaiwen Leon Song , Dingwen Tao

Learning across domains is challenging when data cannot be centralized due to privacy or heterogeneity, which limits the ability to train a single comprehensive model. Model merging provides an appealing alternative by consolidating…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-16 Junming Liu , Yusen Zhang , Rongchao Zhang , Wenkai Zhu , Tian Wu

First-order methods like stochastic gradient descent(SGD) are recently the popular optimization method to train deep neural networks (DNNs), but second-order methods are scarcely used because of the overpriced computing cost in getting the…

Machine Learning · Computer Science 2021-04-01 Jingcheng Zhou , Wei Wei , Zhiming Zheng

In this paper, we advance a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems. This numerical sampling concept averages DNN outputs produced by a finite set of feature…

Machine Learning · Computer Science 2016-09-08 Christian Huemmer , Ramón Fernández Astudillo , Walter Kellermann

Hessian-free (HF) optimization has been successfully used for training deep autoencoders and recurrent networks. HF uses the conjugate gradient algorithm to construct update directions through curvature-vector products that can be computed…

Machine Learning · Computer Science 2013-05-02 Ryan Kiros

This paper develops an asymptotic theory for two-step debiased machine learning (DML) estimators in generalised method of moments (GMM) models with general multiway clustered dependence, without relying on cross-fitting. While cross-fitting…

Econometrics · Economics 2026-04-07 Kaicheng Chen , Harold D. Chiang

Financial time series forecasting in zero-shot settings is critical for investment decisions, especially during abrupt market regime shifts or in emerging markets with limited historical data. While Model-Agnostic Meta-Learning (MAML)…

Machine Learning · Computer Science 2025-08-04 Anxian Liu , Junying Ma , Guang Zhang

The conventional deep learning approaches for solving time-series problem such as long-short term memory (LSTM) and gated recurrent unit (GRU) both consider the time-series data sequence as the input with one single unit as the output…

Signal Processing · Electrical Eng. & Systems 2020-07-01 Xiaoming Li , Chun Wang , Xiao Huang , Yimin Nie

In this paper, the problem of optimal gradient lossless compression in Deep Neural Network (DNN) training is considered. Gradient compression is relevant in many distributed DNN training scenarios, including the recently popular federated…

Machine Learning · Computer Science 2021-11-16 Zhong-Jing Chen , Eduin E. Hernandez , Yu-Chih Huang , Stefano Rini

Always-on spoken language interfaces, e.g. personal digital assistants, rely on a wake word to start processing spoken input. We present novel methods to train a hybrid DNN/HMM wake word detection system from partially labeled training…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-30 Yiming Wang , Hang Lv , Daniel Povey , Lei Xie , Sanjeev Khudanpur

In this paper, we propose a generalized framework for developing learning-rate-free momentum stochastic gradient descent (SGD) methods in the minimization of nonsmooth nonconvex functions, especially in training nonsmooth neural networks.…

Optimization and Control · Mathematics 2024-06-27 Xiaoyin Hu , Nachuan Xiao , Xin Liu , Kim-Chuan Toh

It is hard to train Recurrent Neural Network (RNN) with stable convergence and avoid gradient vanishing and exploding problems, as the weights in the recurrent unit are repeated from iteration to iteration. Moreover, RNN is sensitive to the…

Machine Learning · Computer Science 2022-03-29 Yu Tang , Zhigang Kan , Dequan Sun , Jingjing Xiao , Zhiquan Lai , Linbo Qiao , Dongsheng Li