English
Related papers

Related papers: Second-Order Forward-Mode Automatic Differentiatio…

200 papers

We propose a multi-step training method for designing generalized linear classifiers. First, an initial multi-class linear classifier is found through regression. Then validation error is minimized by pruning of unnecessary inputs.…

Machine Learning · Computer Science 2023-12-15 Kanishka Tyagi , Chinmay Rane , Michael Manry

We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning, including hyperparameter optimization, loss function learning, few-shot learning, invariance learning and more. These problems are often…

Machine Learning · Computer Science 2024-10-15 Minyoung Kim , Timothy M. Hospedales

This paper addresses second-order stochastic optimization for estimating the minimizer of a convex function written as an expectation. A direct recursive estimation technique for the inverse Hessian matrix using a Robbins-Monro procedure is…

Optimization and Control · Mathematics 2025-03-11 Antoine Godichon-Baggioni , Wei Lu , Bruno Portier

Higher-order tensor methods were recently proposed for minimizing smooth convex and nonconvex functions. Higher-order algorithms accelerate the convergence of the classical first-order methods thanks to the higher-order derivatives used in…

Optimization and Control · Mathematics 2024-01-11 Ion Necoara

We design an algorithm which finds an $\epsilon$-approximate stationary point (with $\|\nabla F(x)\|\le \epsilon$) using $O(\epsilon^{-3})$ stochastic gradient and Hessian-vector products, matching guarantees that were previously available…

Machine Learning · Computer Science 2020-06-25 Yossi Arjevani , Yair Carmon , John C. Duchi , Dylan J. Foster , Ayush Sekhari , Karthik Sridharan

When training deep learning models, the performance depends largely on the selected hyperparameters. However, hyperparameter optimization (HPO) is often one of the most expensive parts of model design. Classical HPO methods treat this as a…

Prior flow matching methods in robotics have primarily learned velocity fields to morph one distribution of trajectories into another. In this work, we extend flow matching to capture second-order trajectory dynamics, incorporating…

Robotics · Computer Science 2025-03-11 Khang Nguyen , An T. Le , Tien Pham , Manfred Huber , Jan Peters , Minh Nhat Vu

Several machine learning applications involve the optimization of higher-order derivatives (e.g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation. As a…

Machine Learning · Computer Science 2020-11-26 Tianyu Pang , Kun Xu , Chongxuan Li , Yang Song , Stefano Ermon , Jun Zhu

We present a second order algorithm, based on orthantwise directions, for solving optimization problems involving the sparsity enhancing $\ell_1$-norm. The main idea of our method consists in modifying the descent orthantwise directions by…

Optimization and Control · Mathematics 2016-07-05 J. C. De los Reyes , E. Loayza , P. Merino

We present novel algorithms for simulation optimization using random directions stochastic approximation (RDSA). These include first-order (gradient) as well as second-order (Newton) schemes. We incorporate both continuous-valued as well as…

Optimization and Control · Mathematics 2015-08-11 Prashanth L. A. , Shalabh Bhatnagar , Michael Fu , Steve Marcus

This paper considers distributed optimization problems, where each agent cooperatively minimizes the sum of local objective functions through the communication with its neighbors. The widely adopted distributed gradient method in solving…

Optimization and Control · Mathematics 2025-08-19 Yeming Xu , Ziyuan Guo , Kaihong Lu , Huanshui Zhang

In recent studies, line search methods have shown significant improvements in the performance of traditional stochastic gradient descent techniques, eliminating the need for a specific learning rate schedule. In this paper, we identify…

Machine Learning · Computer Science 2024-03-28 Philip Kenneweg , Tristan Kenneweg , Barbara Hammer

Bilevel optimization has arisen as a powerful tool in modern machine learning. However, due to the nested structure of bilevel optimization, even gradient-based methods require second-order derivative approximations via Jacobian- or/and…

Machine Learning · Computer Science 2022-06-07 Daouda Sow , Kaiyi Ji , Yingbin Liang

The back-propagation algorithm has long been the de-facto standard in optimizing weights and biases in neural networks, particularly in cutting-edge deep learning models. Its widespread adoption in fields like natural language processing,…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Sidike Paheding , Abel A. Reyes-Angulo

In this paper we develop a Bayesian optimization based hyperparameter tuning framework inspired by statistical learning theory for classifiers. We utilize two key facts from PAC learning theory; the generalization bound will be higher for a…

Machine Learning · Computer Science 2019-02-08 Tinu Theckel Joy , Santu Rana , Sunil Gupta , Svetha Venkatesh

Zeroth-order or derivative-free optimization (MeZO) is an attractive strategy for finetuning large language models (LLMs) because it eliminates the memory overhead of backpropagation. However, it converges slowly due to the inherent curse…

Machine Learning · Computer Science 2026-04-21 Lejs Deen Behric , Liang Zhang , Bingcong Li , Kiran Koshy Thekumparampil

Stochastic second-order methods achieve fast local convergence in strongly convex optimization by using noisy Hessian estimates to precondition the gradient. However, these methods typically reach superlinear convergence only when the…

Optimization and Control · Mathematics 2024-11-12 Ruichen Jiang , Michał Dereziński , Aryan Mokhtari

The performance of deep neural networks is highly sensitive to the choice of the hyperparameters that define the structure of the network and the learning process. When facing a new application, tuning a deep neural network is a tedious and…

Machine Learning · Computer Science 2019-07-04 Dounia Lakhmiri , Sébastien Le Digabel , Christophe Tribes

The gradients used to train neural networks are typically computed using backpropagation. While an efficient way to obtain exact gradients, backpropagation is computationally expensive, hinders parallelization, and is biologically…

Machine Learning · Computer Science 2026-01-14 Katharina Flügel , Daniel Coquelin , Marie Weiel , Charlotte Debus , Achim Streit , Markus Götz

These notes focus on the minimization of convex functionals using first-order optimization methods, which are fundamental in many areas of applied mathematics and engineering. The primary goal of this document is to introduce and analyze…

Optimization and Control · Mathematics 2024-10-28 Charles Dossal , Samuel Hurault , Nicolas Papadakis