English
Related papers

Related papers: Initialization of a Polyharmonic Cascade, Launch a…

200 papers

Gradient descent and coordinate descent are well understood in terms of their asymptotic behavior, but less so in a transient regime often used for approximations in machine learning. We investigate how proper initialization can have a…

Machine Learning · Computer Science 2017-06-14 Hadi Daneshmand , Hamed Hassani , Thomas Hofmann

Machine learning is the dominant approach to artificial intelligence, through which computers learn from data and experience. In the framework of supervised learning, a necessity for a computer to learn from data accurately and efficiently…

Machine Learning · Statistics 2023-01-25 Amir R. Asadi

The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance. Yet…

Machine Learning · Computer Science 2020-01-17 Wei Hu , Lechao Xiao , Jeffrey Pennington

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be…

Hardware Architecture · Computer Science 2023-12-22 Qing Zhang , Cheng Liu , Bo Liu , Haitong Huang , Ying Wang , Huawei Li , Xiaowei Li

Maintaining the pair similarity relationship among originally high-dimensional data into a low-dimensional binary space is a popular strategy to learn binary codes. One simiple and intutive method is to utilize two identical code matrices…

Information Retrieval · Computer Science 2018-11-28 Xiaoshuang Shi , Fuyong Xing , Zizhao Zhang , Manish Sapkota , Zhenhua Guo , Lin Yang

We generalize the Hamiltonian Monte Carlo algorithm with a stack of neural network layers and evaluate its ability to sample from different topologies in a two dimensional lattice gauge theory. We demonstrate that our model is able to…

High Energy Physics - Lattice · Physics 2021-05-10 Sam Foreman , Xiao-Yong Jin , James C. Osborn

This paper is about metric data structures in high-dimensional or non-Euclidean space that permit cached sufficient statistics accelerations of learning algorithms. It has recently been shown that for less than about 10 dimensions,…

Machine Learning · Computer Science 2013-01-18 Andrew Moore

Presented in this paper is a new sparse linear solver methodology motivated by multigrid principles and based around general local transformations that diagonalize a matrix while maintaining its sparsity. These transformations are…

Numerical Analysis · Mathematics 2007-05-23 Jonathan E. Moussa

PolyChord is a novel nested sampling algorithm tailored for high dimensional parameter spaces. In addition, it can fully exploit a hierarchy of parameter speeds such as is found in CosmoMC and CAMB. It utilises slice sampling at each…

Cosmology and Nongalactic Astrophysics · Physics 2015-06-23 W. J. Handley , M. P. Hobson , A. N. Lasenby

We present a novel deep learning approach to approximate the solution of large, sparse, symmetric, positive-definite linear systems of equations. These systems arise from many problems in applied science, e.g., in numerical methods for…

Machine Learning · Computer Science 2022-10-04 Ayano Kaneda , Osman Akar , Jingyu Chen , Victoria Kala , David Hyde , Joseph Teran

In this paper, we present a novel algorithm that integrates deep learning with the polycube method (DL-Polycube) to generate high-quality hexahedral (hex) meshes, which are then used to construct volumetric splines for isogeometric…

Computational Geometry · Computer Science 2024-10-25 Yuxuan Yu , Yuzhuo Fang , Hua Tong , Yongjie Jessica Zhang

Developing efficient and guaranteed nonconvex algorithms has been an important challenge in modern machine learning. Algorithms with good empirical performance such as stochastic gradient descent often lack theoretical guarantees. In this…

Machine Learning · Statistics 2017-06-15 Anima Anandkumar , Yuan Deng , Rong Ge , Hossein Mobahi

Asynchronous distributed algorithms are a popular way to reduce synchronization costs in large-scale optimization, and in particular for neural network training. However, for nonsmooth and nonconvex objectives, few convergence guarantees…

Optimization and Control · Mathematics 2020-07-14 Vyacheslav Kungurtsev , Malcolm Egan , Bapi Chatterjee , Dan Alistarh

Sample-based quantum diagonalization (SQD) is an algorithm for hybrid quantum-classical molecular simulation that has been of broad interest for application with noisy intermediate scale quantum (NISQ) devices. However, SQD does not always…

Quantum Physics · Physics 2025-12-05 L. Andrew Wray , Cheng-Ju Lin , Vincent Su , Hrant Gharibyan

Subspace clustering refers to the problem of clustering high-dimensional data into a union of low-dimensional subspaces. Current subspace clustering approaches are usually based on a two-stage framework. In the first stage, an affinity…

Machine Learning · Computer Science 2019-10-22 Shuai Yang , Wenqi Zhu , Yuesheng Zhu

Deep ensembles have been empirically shown to be a promising approach for improving accuracy, uncertainty and out-of-distribution robustness of deep learning models. While deep ensembles were theoretically motivated by the bootstrap,…

Machine Learning · Statistics 2020-06-26 Stanislav Fort , Huiyi Hu , Balaji Lakshminarayanan

Deep learning has achieved a remarkable performance breakthrough in several fields, most notably in speech recognition, natural language processing, and computer vision. In particular, convolutional neural network (CNN) architectures…

Computer Vision and Pattern Recognition · Computer Science 2016-12-08 Federico Monti , Davide Boscaini , Jonathan Masci , Emanuele Rodolà , Jan Svoboda , Michael M. Bronstein

Over the past five decades, k-means has become the clustering algorithm of choice in many application domains primarily due to its simplicity, time/space efficiency, and invariance to the ordering of the data points. Unfortunately, the…

Machine Learning · Computer Science 2014-09-16 M. Emre Celebi , Hassan A. Kingravi

Universal unitary photonic devices can apply arbitrary unitary transformations to a vector of input modes and provide a promising hardware platform for fast and energy-efficient machine learning using light. We simulate the gradient-based…

Signal Processing · Electrical Eng. & Systems 2019-06-26 Sunil Pai , Ben Bartlett , Olav Solgaard , David A. B. Miller

Developing robust representations of chemical structures that enable models to learn topological inductive biases is challenging. In this manuscript, we present a representation of atomistic systems. We begin by proving that our…

Machine Learning · Computer Science 2024-09-27 Rahul Khorana , Marcus Noack , Jin Qian