English
Related papers

Related papers: Tune without Validation: Searching for Learning Ra…

200 papers

Deep neural networks have been very successful in image estimation applications such as compressive-sensing and image restoration, as a means to estimate images from partial, blurry, or otherwise degraded measurements. These networks are…

Computer Vision and Pattern Recognition · Computer Science 2019-10-30 Zhihao Xia , Ayan Chakrabarti

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Jinhee Kim , Jae Jun An , Kang Eun Jeon , Jong Hwan Ko

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

Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures…

Machine Learning · Computer Science 2018-06-19 Utku Evci

Batch normalization (BN) is a key facilitator and considered essential for state-of-the-art binary neural networks (BNN). However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle…

Machine Learning · Computer Science 2021-04-19 Tianlong Chen , Zhenyu Zhang , Xu Ouyang , Zechun Liu , Zhiqiang Shen , Zhangyang Wang

Statistical mechanics is used to study unrealizable generalization in two large feed-forward neural networks with binary weights and output, a perceptron and a tree committee machine. The student is trained by a teacher being larger, i.e.…

Condensed Matter · Physics 2007-05-23 Matts Sporre

A particle filtering approach is suggested for the training of multi-layer neural networks without utilizing gradients calculation. The network weights are considered to be the components of the estimated state-vector of a noise driven…

Optimization and Control · Mathematics 2020-10-13 Isaac Yaesh , Natan Grinfeld

We introduce a novel class of variable selection penalties called TWIN, which provides sensible data-adaptive penalization. Under a linear sparsity regime and random Gaussian designs we show that penalties in the TWIN class have a high…

Methodology · Statistics 2018-06-07 Xiaowu Dai , Jared D. Huling

In this paper, we present a statistical-mechanical analysis of deep learning. We elucidate some of the essential components of deep learning---pre-training by unsupervised learning and fine tuning by supervised learning. We formulate the…

Machine Learning · Statistics 2015-06-23 Masayuki Ohzeki

Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning uniformly regardless of problem difficulty. We propose Hint Tuning, a data-efficient…

Computation and Language · Computer Science 2026-05-12 Siqi Fan , Minghao Li , Xiaoqian Ma , Xiusheng Huang , Zhuo Chen , Bowen Qin , Liujie Zhang , Shuo Shang , Weihang Chen

A common way to avoid overfitting in supervised learning is early stopping, where a held-out set is used for iterative evaluation during training to find a sweet spot in the number of training steps that gives maximum generalization.…

Machine Learning · Computer Science 2022-08-23 Ali Vardasbi , Maarten de Rijke , Mostafa Dehghani

Quantization and pruning are core techniques used to reduce the inference costs of deep neural networks. State-of-the-art quantization techniques are currently applied to both the weights and activations; however, pruning is most often…

Machine Learning · Computer Science 2021-11-02 Xinyu Zhang , Ian Colbert , Ken Kreutz-Delgado , Srinjoy Das

Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applications. This is a potential issue because of the great amount of computational resources needed for training, and of the possible loss of…

Computation and Language · Computer Science 2022-10-31 Giovanni Bonetta , Matteo Ribero , Rossella Cancelliere

Loss of trainability refers to a phenomenon in continual learning where parameter updates no longer make progress on the optimization objective, so accuracy stalls or degrades as the learning problem changes over time. In this paper, we…

Machine Learning · Computer Science 2025-12-11 Gunbir Singh Baveja , Alex Lewandowski , Mark Schmidt

We introduce an exploratory study on Mutation Validation (MV), a model validation method using mutated training labels for supervised learning. MV mutates training data labels, retrains the model against the mutated data, then uses the…

Machine Learning · Computer Science 2021-10-22 Jie M. Zhang , Mark Harman , Benjamin Guedj , Earl T. Barr , John Shawe-Taylor

This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights…

Computation and Language · Computer Science 2018-02-23 Prajit Ramachandran , Peter J. Liu , Quoc V. Le

For most deep learning algorithms training is notoriously time consuming. Since most of the computation in training neural networks is typically spent on floating point multiplications, we investigate an approach to training that eliminates…

Machine Learning · Computer Science 2016-02-29 Zhouhan Lin , Matthieu Courbariaux , Roland Memisevic , Yoshua Bengio

The success of deep neural networks is in part due to the use of normalization layers. Normalization layers like Batch Normalization, Layer Normalization and Weight Normalization are ubiquitous in practice, as they improve generalization…

Machine Learning · Computer Science 2020-06-15 Yonatan Dukler , Quanquan Gu , Guido Montúfar

Deep neural network (NN) with millions or billions of parameters can perform really well on unseen data, after being trained from a finite training set. Various prior theories have been developed to explain such excellent ability of NNs,…

Machine Learning · Computer Science 2025-03-11 Khoat Than , Dat Phan

We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for computing the parameters gradients. During…

Machine Learning · Computer Science 2016-03-18 Matthieu Courbariaux , Itay Hubara , Daniel Soudry , Ran El-Yaniv , Yoshua Bengio