English
Related papers

Related papers: Gradient Descent: The Ultimate Optimizer

200 papers

Deep networks excel in learning patterns from large amounts of data. On the other hand, many geometric vision tasks are specified as optimization problems. To seamlessly combine deep learning and geometric vision, it is vital to perform…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Bo Chen , Alvaro Parra , Jiewei Cao , Nan Li , Tat-Jun Chin

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

Computing the gradient of a function provides fundamental information about its behavior. This information is essential for several applications and algorithms across various fields. One common application that require gradients are…

Numerical Analysis · Mathematics 2022-06-09 Esmail Abdul Fattah , Janet Van Niekerk , Haavard Rue

Training a neural network with the gradient descent algorithm gives rise to a discrete-time nonlinear dynamical system. Consequently, behaviors that are typically observed in these systems emerge during training, such as convergence to an…

Machine Learning · Computer Science 2018-10-10 Kamil Nar , S. Shankar Sastry

The backtracking line-search is an effective technique to automatically tune the step-size in smooth optimization. It guarantees similar performance to using the theoretically optimal step-size. Many approaches have been developed to…

Optimization and Control · Mathematics 2023-06-06 Frederik Kunstner , Victor S. Portella , Mark Schmidt , Nick Harvey

Deep neural networks have seen great success in recent years; however, training a deep model is often challenging as its performance heavily depends on the hyper-parameters used. In addition, finding the optimal hyper-parameter…

In this paper, we establish new convergence results for the quantized distributed gradient descent and suggest a novel strategy of choosing the stepsizes for the high-performance of the algorithm. Under the strongly convexity assumption on…

Optimization and Control · Mathematics 2023-07-03 Woocheol Choi , Myeong-Su Lee

Automatic differentiation frameworks are optimized for exactly one thing: computing the average mini-batch gradient. Yet, other quantities such as the variance of the mini-batch gradients or many approximations to the Hessian can, in…

Machine Learning · Computer Science 2020-02-18 Felix Dangel , Frederik Kunstner , Philipp Hennig

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study…

Optimization and Control · Mathematics 2018-10-30 Lenaic Chizat , Francis Bach

The success of deep learning over the past decade mainly relies on gradient-based optimisation and backpropagation. This paper focuses on analysing the performance of first-order gradient-based optimisation algorithms, gradient descent and…

Optimization and Control · Mathematics 2022-12-08 Behnam Mafakheri , Iman Shames , Jonathan H. Manton

Motivated by the problem of tuning hyperparameters in machine learning, we present a new approach for gradually and adaptively optimizing an unknown function using estimated gradients. We validate the empirical performance of the proposed…

Machine Learning · Computer Science 2019-06-05 Weijia Shao , Christian Geißler , Fikret Sivrikaya

Forward gradients have been recently introduced to bypass backpropagation in autodifferentiation, while retaining unbiased estimators of true gradients. We derive an optimality condition to obtain best approximating forward gradients, which…

Machine Learning · Computer Science 2022-09-15 Gabriel Belouze

Embedding parameterized optimization problems as layers into machine learning architectures serves as a powerful inductive bias. Training such architectures with stochastic gradient descent requires care, as degenerate derivatives of the…

Machine Learning · Computer Science 2024-12-16 Anselm Paulus , Georg Martius , Vít Musil

We propose a first-order method for convex optimization, where instead of being restricted to the gradient from a single parameter, gradients from multiple parameters can be used during each step of gradient descent. This setup is…

Machine Learning · Computer Science 2023-02-08 Yash Chandak , Shiv Shankar , Venkata Gandikota , Philip S. Thomas , Arya Mazumdar

Optimizing machine learning algorithms that are used to solve the objective function has been of great interest. Several approaches to optimize common algorithms, such as gradient descent and stochastic gradient descent, were explored. One…

Machine Learning · Computer Science 2022-10-06 Hilal AlQuabeh , Farha AlBreiki , Dilshod Azizov

A subgradient method is presented for solving general convex optimization problems, the main requirement being that a strictly-feasible point is known. A feasible sequence of iterates is generated, which converges to within user-specified…

Optimization and Control · Mathematics 2016-05-30 James Renegar

We present a novel optimization-based decoding algorithm for LDPC codes that is suitable for hardware architectures specialized to feed-forward neural networks. The algorithm is based on the projected gradient descent algorithm with a…

Information Theory · Computer Science 2019-01-16 Tadashi Wadayama , Satoshi Takabe

The backpropagation algorithm, which had been originally introduced in the 1970s, is the workhorse of learning in neural networks. This backpropagation algorithm makes use of the famous machine learning algorithm known as Gradient Descent,…

Machine Learning · Computer Science 2018-02-02 Varun Ranganathan , S. Natarajan

We consider the problem of maximizing a convex function over a closed convex set in a real Hilbert space. For linear functions, we show that a single orthogonal projection suffices to obtain an approximate solution. For continuous convex…

Optimization and Control · Mathematics 2026-02-23 Pedro Felzenszwalb , Heon Lee

Iterative algorithms, like gradient descent, are common tools for solving a variety of problems, such as model fitting. For this reason, there is interest in creating differentially private versions of them. However, their conversion to…

Machine Learning · Computer Science 2018-08-30 Jaewoo Lee , Daniel Kifer