English
Related papers

Related papers: Large-Scale Riemannian Meta-Optimization via Subsp…

200 papers

We introduce two complementary techniques for efficient optimization that reduce memory requirements while accelerating training of large-scale neural networks. The first technique, Subset-Norm step size, generalizes AdaGrad-Norm and…

Machine Learning · Computer Science 2025-05-27 Thien Hang Nguyen , Huy Le Nguyen

In this paper, we propose a machine learning (ML) method to learn how to solve a generic constrained continuous optimization problem. To the best of our knowledge, the generic methods that learn to optimize, focus on unconstrained…

Machine Learning · Computer Science 2021-01-05 Seyedrazieh Bayati , Faramarz Jabbarvaziri

Recent years have seen deep neural networks (DNNs) becoming wider and deeper to achieve better performance in many applications of AI. Such DNNs however require huge amounts of memory to store weights and intermediate results (e.g.,…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-04-27 Taro Sekiyama , Takashi Imamichi , Haruki Imai , Rudy Raymond

Batch Normalization (BN) has proven to be an effective algorithm for deep neural network training by normalizing the input to each neuron and reducing the internal covariate shift. The space of weight vectors in the BN layer can be…

Machine Learning · Computer Science 2017-11-01 Minhyung Cho , Jaehyung Lee

In image set classification, a considerable advance has been made by modeling the original image sets by second order statistics or linear subspace, which typically lie on the Riemannian manifold. Specifically, they are Symmetric Positive…

Computer Vision and Pattern Recognition · Computer Science 2018-05-31 Rui Wang , Xiao-Jun Wu , Kai-Xuan Chen , Josef Kittler

Conventional hyperparameter optimization methods are computationally intensive and hard to generalize to scenarios that require dynamically adapting hyperparameters, such as life-long learning. Here, we propose an online hyperparameter…

Machine Learning · Computer Science 2021-04-09 Daniel Jiwoong Im , Cristina Savin , Kyunghyun Cho

Under the data manifold hypothesis, high-dimensional data are concentrated near a low-dimensional manifold. We study the problem of Riemannian optimization over such manifolds when they are given only implicitly through the data…

Machine Learning · Computer Science 2026-03-03 Andrey Kharitenko , Zebang Shen , Riccardo de Santi , Niao He , Florian Doerfler

Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular…

Machine Learning · Computer Science 2017-10-20 Dawit Mureja , Hyunsin Park , Chang D. Yoo

Gradient descent with momentum has been widely applied in various signal processing and machine learning tasks, demonstrating a notable empirical advantage over standard gradient descent. However, momentum-based distributed Riemannian…

Optimization and Control · Mathematics 2026-02-17 Jun Chen , Tianyi Zhu , Haishan Ye , Lina Liu , Guang Dai , Yong Liu , Yunliang Jiang , Ivor W. Tsang

A core capability of intelligent systems is the ability to quickly learn new tasks by drawing on prior experience. Gradient (or optimization) based meta-learning has recently emerged as an effective approach for few-shot learning. In this…

Machine Learning · Computer Science 2019-09-11 Aravind Rajeswaran , Chelsea Finn , Sham Kakade , Sergey Levine

Constrained optimization plays a crucial role in the fields of quantum physics and quantum information science and becomes especially challenging for high-dimensional complex structure problems. One specific issue is that of quantum process…

Quantum Physics · Physics 2024-04-30 Daniel Volya , Andrey Nikitin , Prabhat Mishra

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

Machine Learning · Computer Science 2021-05-06 Kurtland Chua , Qi Lei , Jason D. Lee

By restricting the iterate on a nonlinear manifold, the recently proposed Riemannian optimization methods prove to be both efficient and effective in low rank tensor completion problems. However, existing methods fail to exploit the easily…

Machine Learning · Statistics 2017-02-24 Tengfei Zhou , Hui Qian , Zebang Shen , Congfu Xu

Conjugate gradient (CG) methods are widely acknowledged as efficient for minimizing continuously differentiable functions in Euclidean spaces. In recent years, various CG methods have been extended to Riemannian manifold optimization, but…

Optimization and Control · Mathematics 2026-05-26 Chunming Tang , Shaohui Liang , Huangyue Chen

With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…

Machine Learning · Computer Science 2024-07-02 Jingran Shen , Nikos Tziritas , Georgios Theodoropoulos

Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the real world. This situation has led to research into model…

Machine Learning · Computer Science 2020-05-29 Muhammad A. Shah , Raphael Olivier , Bhiksha Raj

Manifold learning is used for dimensionality reduction, with the goal of finding a projection subspace to increase and decrease the inter- and intraclass variances, respectively. However, a bottleneck for subspace learning methods often…

Machine Learning · Computer Science 2021-05-26 Parisa Abdolrahim Poorheravi , Vincent Gaudet

We address the challenge of optimizing meta-parameters (hyperparameters) in machine learning, a key factor for efficient training and high model performance. Rather than relying on expensive meta-parameter search methods, we introduce…

Machine Learning · Computer Science 2025-07-10 Arsalan Sharifnassab , Saber Salehkaleybar , Richard Sutton

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…

Machine Learning · Computer Science 2021-03-31 Giulia Denevi , Massimiliano Pontil , Carlo Ciliberto

Compared to classical deep neural networks its binarized versions can be useful for applications on resource-limited devices due to their reduction in memory consumption and computational demands. In this work we study deep neural networks…

Optimization and Control · Mathematics 2021-10-26 Jannis Kurtz , Bubacarr Bah