English
Related papers

Related papers: adaQN: An Adaptive Quasi-Newton Algorithm for Trai…

200 papers

The RNN-Transducer (RNN-T) framework for speech recognition has been growing in popularity, particularly for deployed real-time ASR systems, because it combines high accuracy with naturally streaming recognition. One of the drawbacks of…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-28 Fangjun Kuang , Liyong Guo , Wei Kang , Long Lin , Mingshuang Luo , Zengwei Yao , Daniel Povey

The ability to train Deep Neural Networks (DNNs) with constraints is instrumental in improving the fairness of modern machine-learning models. Many algorithms have been analysed in recent years, and yet there is no standard, widely accepted…

Machine Learning · Computer Science 2026-02-19 Andrii Kliachkin , Jana Lepšová , Gilles Bareilles , Jakub Mareček

Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed, and is thus useful for implementation in resource-constrained devices. However, it is still hard for extremely low-bit…

Computer Vision and Pattern Recognition · Computer Science 2021-11-03 Kohei Yamamoto

Deep neural networks (DNNs) are so over-parametrized that recent research has found them to already contain a subnetwork with high accuracy at their randomly initialized state. Finding these subnetworks is a viable alternative training…

Computer Vision and Pattern Recognition · Computer Science 2021-11-25 Ángel López García-Arias , Masanori Hashimoto , Masato Motomura , Jaehoon Yu

In this research a novel stochastic gradient descent based learning approach for the radial basis function neural networks (RBFNN) is proposed. The proposed method is based on the q-gradient which is also known as Jackson derivative. In…

Deep Neural Networks(DNNs) have many parameters and activation data, and these both are expensive to implement. One method to reduce the size of the DNN is to quantize the pre-trained model by using a low-bit expression for weights and…

Computer Vision and Pattern Recognition · Computer Science 2020-11-26 Jun Nishikawa , Ryoji Ikegaya

The problem of minimizing an objective that can be written as the sum of a set of $n$ smooth and strongly convex functions is considered. The Incremental Quasi-Newton (IQN) method proposed here belongs to the family of stochastic and…

Optimization and Control · Mathematics 2017-03-29 Aryan Mokhtari , Mark Eisen , Alejandro Ribeiro

We present a novel definition of the reinforcement learning state, actions and reward function that allows a deep Q-network (DQN) to learn to control an optimization hyperparameter. Using Q-learning with experience replay, we train two DQNs…

Optimization and Control · Mathematics 2016-06-21 Samantha Hansen

The demand for high speed data transmission has increased rapidly, leading to advanced optical communication techniques. In the past few years, multiple equalizers based on neural network (NN) have been proposed to recover signal from…

Signal Processing · Electrical Eng. & Systems 2020-08-26 Qingyi Zhou , Fan Zhang , Chuanchuan Yang

Despite their success, convolutional neural networks are computationally expensive because they must examine all image locations. Stochastic attention-based models have been shown to improve computational efficiency at test time, but they…

Machine Learning · Computer Science 2015-09-24 Jimmy Ba , Roger Grosse , Ruslan Salakhutdinov , Brendan Frey

Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are…

Machine Learning · Computer Science 2023-12-27 Gianni Franchi , Olivier Laurent , Maxence Leguéry , Andrei Bursuc , Andrea Pilzer , Angela Yao

We investigate the computational complexity of various problems for simple recurrent neural networks (RNNs) as formal models for recognizing weighted languages. We focus on the single-layer, ReLU-activation, rational-weight RNNs with…

Formal Languages and Automata Theory · Computer Science 2018-03-06 Yining Chen , Sorcha Gilroy , Andreas Maletti , Jonathan May , Kevin Knight

This paper examines the use of Quantized Neural Networks (QNNs) for two resource-constrained scientific applications: automated calibration of semi-conductor quantum bits (qubits) and scientific particle detectors. We evaluate the…

This paper introduces Q-learning with gradient target tracking, a novel reinforcement learning framework that provides a learned continuous target update mechanism as an alternative to the conventional hard update paradigm. In the standard…

Machine Learning · Computer Science 2025-07-21 Bum Geun Park , Taeho Lee , Donghwan Lee

Query rewriting is a crucial technique for passage retrieval in open-domain conversational question answering (CQA). It decontexualizes conversational queries into self-contained questions suitable for off-the-shelf retrievers. Existing…

Computation and Language · Computer Science 2024-06-18 Tianhua Zhang , Kun Li , Hongyin Luo , Xixin Wu , James Glass , Helen Meng

Several variants of recurrent neural networks (RNNs) with orthogonal or unitary recurrent matrices have recently been developed to mitigate the vanishing/exploding gradient problem and to model long-term dependencies of sequences. However,…

Machine Learning · Computer Science 2019-11-20 Kyle Helfrich , Qiang Ye

Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs). Certified robustness, which provides provable guarantees about a model's ability to withstand different adversarial…

Machine Learning · Computer Science 2026-04-29 Yuchen Yang , Yifan Zhao , Shubham Ugare , Gagandeep Singh , Sasa Misailovic

Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks. However, in general, RNNs have a large number of parameters and involve enormous computational costs by repeating the recurrent structures in many…

Machine Learning · Statistics 2024-03-25 Takashi Furuya , Kazuma Suetake , Koichi Taniguchi , Hiroyuki Kusumoto , Ryuji Saiin , Tomohiro Daimon

The non-convexity of the artificial neural network (ANN) training landscape brings inherent optimization difficulties. While the traditional back-propagation stochastic gradient descent (SGD) algorithm and its variants are effective in…

Machine Learning · Computer Science 2025-06-18 Yatong Bai , Tanmay Gautam , Somayeh Sojoudi

Stochastic variance reduction algorithms have recently become popular for minimizing the average of a large, but finite number of loss functions. The present paper proposes a Riemannian stochastic quasi-Newton algorithm with variance…

Machine Learning · Computer Science 2017-09-19 Hiroyuki Kasai , Hiroyuki Sato , Bamdev Mishra