English
Related papers

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

200 papers

Compressing and pruning large machine learning models has become a critical step towards their deployment in real-world applications. Standard pruning and compression techniques are typically designed without taking the structure of the…

Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of…

We present TWIST, a simple and theoretically explainable self-supervised representation learning method by classifying large-scale unlabeled datasets in an end-to-end way. We employ a siamese network terminated by a softmax operation to…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Feng Wang , Tao Kong , Rufeng Zhang , Huaping Liu , Hang Li

Neural networks are often biased to spuriously correlated features that provide misleading statistical evidence that does not generalize. This raises an interesting question: ``Does an optimal unbiased functional subnetwork exist in a…

Machine Learning · Computer Science 2023-06-27 Geon Yeong Park , Sangmin Lee , Sang Wan Lee , Jong Chul Ye

Training neural networks requires significant computational resources and energy. Methods like mixed-precision and quantization-aware training reduce bit usage, yet they still depend heavily on computationally expensive gradient-based…

Machine Learning · Computer Science 2025-09-30 Noa Cohen , Omkar Joglekar , Dotan Di Castro , Vladimir Tchuiev , Shir Kozlovsky , Michal Moshkovitz

Data-efficient image classification using deep neural networks in settings, where only small amounts of labeled data are available, has been an active research area in the recent past. However, an objective comparison between published…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Lorenzo Brigato , Björn Barz , Luca Iocchi , Joachim Denzler

Many neural network pruning algorithms proceed in three steps: train the network to completion, remove unwanted structure to compress the network, and retrain the remaining structure to recover lost accuracy. The standard retraining…

Machine Learning · Computer Science 2020-03-06 Alex Renda , Jonathan Frankle , Michael Carbin

Our goal is to enable machine learning systems to be trained interactively. This requires models that perform well and train quickly, without large amounts of hand-labeled data. We take a step forward in this direction by borrowing from…

In the absence of large labelled datasets, self-supervised learning techniques can boost performance by learning useful representations from unlabelled data, which is often more readily available. However, there is often a domain shift…

Machine Learning · Computer Science 2020-06-23 Linus Ericsson , Henry Gouk , Timothy M. Hospedales

Quantization is one of the most effective methods to compress neural networks, which has achieved great success on convolutional neural networks (CNNs). Recently, vision transformers have demonstrated great potential in computer vision.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Zhihang Yuan , Chenhao Xue , Yiqi Chen , Qiang Wu , Guangyu Sun

Training neural networks is a challenging non-convex optimization problem, and backpropagation or gradient descent can get stuck in spurious local optima. We propose a novel algorithm based on tensor decomposition for guaranteed training of…

Machine Learning · Computer Science 2016-01-13 Majid Janzamin , Hanie Sedghi , Anima Anandkumar

Deep convolutional neural networks are known to be unstable during training at high learning rate unless normalization techniques are employed. Normalizing weights or activations allows the use of higher learning rates, resulting in faster…

Machine Learning · Computer Science 2019-12-02 Brendan Ruff , Taylor Beck , Joscha Bach

Given two or more Deep Neural Networks (DNNs) with the same or similar architectures, and trained on the same dataset, but trained with different solvers, parameters, hyper-parameters, regularization, etc., can we predict which DNN will…

Machine Learning · Computer Science 2020-01-28 Charles H. Martin , Michael W. Mahoney

Post-training quantization is an effective method for reducing the serving cost of large language models, where the standard approach is to use a round-to-nearest quantization level scheme. However, this often introduces large errors due to…

Machine Learning · Computer Science 2025-11-26 Ziteng Sun , Adrian Benton , Samuel Kushnir , Asher Trockman , Vikas Singh , Suhas Diggavi , Ananda Theertha Suresh

In this paper, we investigate properties and limitations of invariance learned by neural networks from the data compared to the genuine invariance achieved through invariant weight-tying. To do so, we adopt a group theoretical perspective…

Machine Learning · Computer Science 2023-08-09 Artem Moskalev , Anna Sepliarskaia , Erik J. Bekkers , Arnold Smeulders

Purpose: Simulation-based digital twins represent an effort to provide high-accuracy real-time insights into operational physical processes. However, the computation time of many multi-physical simulation models is far from real-time. It…

Computational Engineering, Finance, and Science · Computer Science 2024-07-08 Maximilian Kannapinn , Michael Schäfer , Oliver Weeger

Imaging is a standard example of an inverse problem, where the task of reconstructing a ground truth from a noisy measurement is ill-posed. Recent state-of-the-art approaches for imaging use deep learning, spearheaded by unrolled and…

Weight decay is a widely used technique for training Deep Neural Networks(DNN). It greatly affects generalization performance but the underlying mechanisms are not fully understood. Recent works show that for layers followed by…

Machine Learning · Computer Science 2021-03-30 Yucong Zhou , Yunxiao Sun , Zhao Zhong

Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achieving high accuracy and avoiding negative transfer. Supervised…

Computer Vision and Pattern Recognition · Computer Science 2021-08-25 Kuniaki Saito , Donghyun Kim , Piotr Teterwak , Stan Sclaroff , Trevor Darrell , Kate Saenko

We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network efficiently learns data distribution, a network is likely to learn the bias information to…

Computer Vision and Pattern Recognition · Computer Science 2019-04-16 Byungju Kim , Hyunwoo Kim , Kyungsu Kim , Sungjin Kim , Junmo Kim