English
Related papers

Related papers: Leveraging Second-Order Curvature for Efficient Le…

200 papers

Optimization in Deep Learning is mainly dominated by first-order methods which are built around the central concept of backpropagation. Second-order optimization methods, which take into account the second-order derivatives are far less…

Machine Learning · Computer Science 2021-04-09 Fares B. Mehouachi , Chaouki Kasmi

Second-order methods have shown state-of-the-art performance for optimizing deep neural networks. Nonetheless, their large memory requirement and high computational complexity, compared to first-order methods, hinder their versatility in a…

Machine Learning · Computer Science 2022-03-08 Ehsan Amid , Rohan Anil , Manfred K. Warmuth

Second-order pooling, a.k.a.~bilinear pooling, has proven effective for deep learning based visual recognition. However, the resulting second-order networks yield a final representation that is orders of magnitude larger than that of…

Computer Vision and Pattern Recognition · Computer Science 2018-07-17 Kaicheng Yu , Mathieu Salzmann

Diagonal preconditioners are computationally feasible approximate to second-order optimizers, which have shown significant promise in accelerating training of deep learning models. Two predominant approaches are based on Adam and…

Machine Learning · Computer Science 2025-10-16 Bingbin Liu , Rachit Bansal , Depen Morwani , Nikhil Vyas , David Alvarez-Melis , Sham M. Kakade

Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulties can be addressed by second-order approaches that apply a…

Machine Learning · Computer Science 2020-04-29 Ted Moskovitz , Rui Wang , Janice Lan , Sanyam Kapoor , Thomas Miconi , Jason Yosinski , Aditya Rawal

Even though rate-distortion optimization is a crucial part of traditional image and video compression, not many approaches exist which transfer this concept to end-to-end-trained image compression. Most frameworks contain static compression…

Image and Video Processing · Electrical Eng. & Systems 2022-01-06 Fabian Brand , Kristian Fischer , Alexander Kopte , André Kaup

Since LIC has made rapid progress recently compared to traditional methods, this paper attempts to discuss the question about 'Where is the boundary of Learned Image Compression(LIC)?'. Thus this paper splits the above problem into two…

Image and Video Processing · Electrical Eng. & Systems 2024-08-05 Jixiang Luo

While the superior performance of second-order optimization methods such as Newton's method is well known, they are hardly used in practice for deep learning because neither assembling the Hessian matrix nor calculating its inverse is…

Machine Learning · Computer Science 2020-09-16 Siyuan Shen , Tianjia Shao , Kun Zhou , Chenfanfu Jiang , Feng Luo , Yin Yang

Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if…

Machine Learning · Computer Science 2017-10-25 Haishan Ye , Zhihua Zhang

A class of second-order algorithms is proposed for minimizing smooth nonconvex functions that alternates between regularized Newton and negative curvature steps in an iteration-dependent subspace. In most cases, the Hessian matrix is…

Optimization and Control · Mathematics 2023-08-22 Serge Gratton , Sadok Jerad , Philippe L. Toint

We present a novel adaptive optimization algorithm for large-scale machine learning problems. Equipped with a low-cost estimate of local curvature and Lipschitz smoothness, our method dynamically adapts the search direction and step-size.…

Machine Learning · Computer Science 2021-09-14 Majid Jahani , Sergey Rusakov , Zheng Shi , Peter Richtárik , Michael W. Mahoney , Martin Takáč

In this paper, we present new second-order algorithms for composite convex optimization, called Contracting-domain Newton methods. These algorithms are affine-invariant and based on global second-order lower approximation for the smooth…

Optimization and Control · Mathematics 2020-12-23 Nikita Doikov , Yurii Nesterov

We consider distributed stochastic optimization problems that are solved with master/workers computation architecture. Statistical arguments allow to exploit statistical similarity and approximate this problem by a finite-sum problem, for…

Second-order optimization has been shown to accelerate the training of deep neural networks in many applications, often yielding faster progress per iteration on the training loss compared to first-order optimizers. However, the…

Machine Learning · Computer Science 2024-11-14 Davide Buffelli , Jamie McGowan , Wangkun Xu , Alexandru Cioba , Da-shan Shiu , Guillaume Hennequin , Alberto Bernacchia

In this paper, we propose a new randomized second-order optimization algorithm---Stochastic Subspace Cubic Newton (SSCN)---for minimizing a high dimensional convex function $f$. Our method can be seen both as a {\em stochastic} extension of…

Optimization and Control · Mathematics 2020-02-25 Filip Hanzely , Nikita Doikov , Peter Richtárik , Yurii Nesterov

Given the massive cost of language model pre-training, a non-trivial improvement of the optimization algorithm would lead to a material reduction on the time and cost of training. Adam and its variants have been state-of-the-art for years,…

Machine Learning · Computer Science 2024-03-06 Hong Liu , Zhiyuan Li , David Hall , Percy Liang , Tengyu Ma

Benefit from flexible network designs and end-to-end joint optimization approach, learned image compression (LIC) has demonstrated excellent coding performance and practical feasibility in recent years. However, existing compression models…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Litian Li , Zheng Yang , Ronggang Wang

Adversarial training is a common approach to improving the robustness of deep neural networks against adversarial examples. In this work, we propose a novel regularization approach as an alternative. To derive the regularizer, we formulate…

Machine Learning · Computer Science 2021-02-09 Avery Ma , Fartash Faghri , Nicolas Papernot , Amir-massoud Farahmand

Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. We…

Machine Learning · Computer Science 2013-03-12 Tommi Vatanen , Tapani Raiko , Harri Valpola , Yann LeCun

Large scale optimization problems are ubiquitous in machine learning and data analysis and there is a plethora of algorithms for solving such problems. Many of these algorithms employ sub-sampling, as a way to either speed up the…

Optimization and Control · Mathematics 2016-02-29 Farbod Roosta-Khorasani , Michael W. Mahoney