English
Related papers

Related papers: A Computationally Efficient Sparsified Online Newt…

200 papers

In this work, we take an experimentally grounded look at neural network optimization. Building on the Shampoo family of algorithms, we identify and alleviate three key issues, resulting in the proposed SPlus method. First, we find that…

Machine Learning · Computer Science 2025-10-27 Kevin Frans , Sergey Levine , Pieter Abbeel

We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands…

Machine Learning · Computer Science 2019-02-27 Trevor Gale , Erich Elsen , Sara Hooker

In this work, we present a globalized stochastic semismooth Newton method for solving stochastic optimization problems involving smooth nonconvex and nonsmooth convex terms in the objective function. We assume that only noisy gradient and…

Optimization and Control · Mathematics 2018-03-12 Andre Milzarek , Xiantao Xiao , Shicong Cen , Zaiwen Wen , Michael Ulbrich

Pruning neural networks reduces inference time and memory costs. On standard hardware, these benefits will be especially prominent if coarse-grained structures, like feature maps, are pruned. We devise two novel saliency-based methods for…

Machine Learning · Computer Science 2023-09-26 Manuel Nonnenmacher , Thomas Pfeil , Ingo Steinwart , David Reeb

We study the sparse phase retrieval problem, which seeks to recover a sparse signal from a limited set of magnitude-only measurements. In contrast to prevalent sparse phase retrieval algorithms that primarily use first-order methods, we…

Information Theory · Computer Science 2024-03-20 Jian-Feng Cai , Yu Long , Ruixue Wen , Jiaxi Ying

Stochastic variance reduction has proven effective at accelerating first-order algorithms for solving convex finite-sum optimization tasks such as empirical risk minimization. Incorporating second-order information has proven helpful in…

Optimization and Control · Mathematics 2025-04-30 Michał Dereziński

Compression techniques are essential in distributed optimization and learning algorithms with high-dimensional model parameters, particularly in scenarios with tight communication constraints such as limited bandwidth. This article presents…

Optimization and Control · Mathematics 2025-10-27 Souvik Das , Subhrakanti Dey

Second-order optimization has been developed to accelerate the training of deep neural networks and it is being applied to increasingly larger-scale models. In this study, towards training on further larger scales, we identify a specific…

Machine Learning · Computer Science 2024-06-11 Satoki Ishikawa , Ryo Karakida

Preconditioned gradient methods are among the most general and powerful tools in optimization. However, preconditioning requires storing and manipulating prohibitively large matrices. We describe and analyze a new structure-aware…

Machine Learning · Computer Science 2018-03-05 Vineet Gupta , Tomer Koren , Yoram Singer

The amount of data in our society has been exploding in the era of big data today. In this paper, we address several open challenges of big data stream classification, including high volume, high velocity, high dimensionality, high…

Machine Learning · Computer Science 2015-07-28 Dayong Wang , Pengcheng Wu , Peilin Zhao , Steven C. H. Hoi

Neural networks can be significantly compressed by pruning, yielding sparse models with reduced storage and computational demands while preserving predictive performance. Model soups (Wortsman et al., 2022) enhance generalization and…

Machine Learning · Computer Science 2024-03-26 Max Zimmer , Christoph Spiegel , Sebastian Pokutta

We propose an online learning algorithm for a class of machine learning models under a separable stochastic approximation framework. The essence of our idea lies in the observation that certain parameters in the models are easier to…

Machine Learning · Computer Science 2023-05-23 Min Gan , Xiang-xiang Su , Guang-yong Chen , Jing Chen

Second-order optimization algorithms exhibit excellent convergence properties for training deep learning models, but often incur significant computation and memory overheads. This can result in lower training efficiency than the first-order…

Machine Learning · Computer Science 2023-08-07 Lin Zhang , Shaohuai Shi , Bo Li

Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environments. Sparse neural networks significantly alleviate these…

Machine Learning · Computer Science 2026-03-16 Jie Ji , Gen Li , Kaiyuan Deng , Fatemeh Afghah , Xiaolong Ma

While first-order optimization methods such as stochastic gradient descent (SGD) are popular in machine learning (ML), they come with well-known deficiencies, including relatively-slow convergence, sensitivity to the settings of…

Optimization and Control · Mathematics 2018-02-19 Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

The recent paradigm shift to large-scale foundation models has brought about a new era for deep learning that, while has found great success in practice, has also been plagued by prohibitively expensive costs in terms of high memory…

Machine Learning · Computer Science 2025-05-21 Stephen Zhang , Vardan Papyan

We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations. Concretely, we introduce a meta sorting network that learns to…

Machine Learning · Computer Science 2020-02-27 Yi Tay , Dara Bahri , Liu Yang , Donald Metzler , Da-Cheng Juan

Network quantization is a dominant paradigm of model compression. However, the abrupt changes in quantized weights during training often lead to severe loss fluctuations and result in a sharp loss landscape, making the gradients unstable…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Jing Liu , Jianfei Cai , Bohan Zhuang

This paper proposes a family of online second order methods for possibly non-convex stochastic optimizations based on the theory of preconditioned stochastic gradient descent (PSGD), which can be regarded as an enhance stochastic Newton…

Machine Learning · Statistics 2018-05-01 Xi-Lin Li

Accelerating the inference speed of CNNs is critical to their deployment in real-world applications. Among all the pruning approaches, those implementing a sparsity learning framework have shown to be effective as they learn and prune the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-31 Jun Shi , Jianfeng Xu , Kazuyuki Tasaka , Zhibo Chen