English
Related papers

Related papers: Second-order Information in First-order Optimizati…

200 papers

Stacking, a heuristic technique for training deep residual networks by progressively increasing the number of layers and initializing new layers by copying parameters from older layers, has proven quite successful in improving the…

Machine Learning · Computer Science 2025-02-20 Naman Agarwal , Pranjal Awasthi , Satyen Kale , Eric Zhao

A new, fast second-order method is proposed that achieves the optimal $\mathcal{O}\left(|\log(\epsilon)|\epsilon^{-3/2}\right)$ complexity to obtain first-order $\epsilon$-stationary points. Crucially, this is deduced without assuming the…

Optimization and Control · Mathematics 2026-02-18 Serge Gratton , Sadok Jerad , Philippe L. Toint

Adaptive optimizers can reduce to normalized steepest descent (NSD) when only adapting to the current gradient, suggesting a close connection between the two algorithmic families. A key distinction between their analyses, however, lies in…

Machine Learning · Computer Science 2025-11-26 Shuo Xie , Tianhao Wang , Beining Wu , Zhiyuan Li

This work proposes a universal and adaptive second-order method for minimizing second-order smooth, convex functions. Our algorithm achieves $O(\sigma / \sqrt{T})$ convergence when the oracle feedback is stochastic with variance $\sigma^2$,…

Optimization and Control · Mathematics 2022-12-13 Kimon Antonakopoulos , Ali Kavis , Volkan Cevher

Due to its simplicity and efficiency, the first-order gradient method has been extensively employed in training neural networks. Although the optimization problem of the neural network is non-convex, recent research has proved that the…

Machine Learning · Computer Science 2024-05-09 Xin Liu , Wei Tao , Wei Li , Dazhi Zhan , Jun Wang , Zhisong Pan

Approximating Stochastic Gradient Descent (SGD) as a Stochastic Differential Equation (SDE) has allowed researchers to enjoy the benefits of studying a continuous optimization trajectory while carefully preserving the stochasticity of SGD.…

Machine Learning · Computer Science 2024-11-04 Sadhika Malladi , Kaifeng Lyu , Abhishek Panigrahi , Sanjeev Arora

We evaluate natural gradient, an algorithm originally proposed in Amari (1997), for learning deep models. The contributions of this paper are as follows. We show the connection between natural gradient and three other recently proposed…

Machine Learning · Computer Science 2014-02-18 Razvan Pascanu , Yoshua Bengio

Two major momentum-based techniques that have achieved tremendous success in optimization are Polyak's heavy ball method and Nesterov's accelerated gradient. A crucial step in all momentum-based methods is the choice of the momentum…

Machine Learning · Statistics 2017-12-21 Vishwak Srinivasan , Adepu Ravi Sankar , Vineeth N Balasubramanian

A very simple first-order algorithm is proposed for solving nonlinear optimization problems with deterministic nonlinear equality constraints. This algorithm adaptively selects steps in the plane tangent to the constraints or steps that…

Optimization and Control · Mathematics 2026-03-11 Serge Gratton , Philippe L. Toint

Gradient descent based optimization methods are the methods of choice to train deep neural networks in machine learning. Beyond the standard gradient descent method, also suitable modified variants of standard gradient descent involving…

Optimization and Control · Mathematics 2025-04-29 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

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

An Adagrad-inspired class of algorithms for smooth unconstrained optimization is presented in which the objective function is never evaluated and yet the gradient norms decrease at least as fast as $\calO(1/\sqrt{k+1})$ while second-order…

Optimization and Control · Mathematics 2023-02-16 S. Gratton , Ph. L. Toint

Alternating minimization (AM) procedures are practically efficient in many applications for solving convex and non-convex optimization problems. On the other hand, Nesterov's accelerated gradient is theoretically optimal first-order method…

Optimization and Control · Mathematics 2021-09-16 Sergey Guminov , Pavel Dvurechensky , Nazarii Tupitsa , Alexander Gasnikov

We investigate the problem of sequential linear data prediction for real life big data applications. The second order algorithms, i.e., Newton-Raphson Methods, asymptotically achieve the performance of the "best" possible linear data…

Data Structures and Algorithms · Computer Science 2017-01-20 Burak C. Civek , Suleyman S. Kozat

Second-order optimization methods offer notable advantages in training deep neural networks by utilizing curvature information to achieve faster convergence. However, traditional second-order techniques are computationally prohibitive,…

Machine Learning · Computer Science 2024-10-04 James Vo

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

Establishing a fast rate of convergence for optimization methods is crucial to their applicability in practice. With the increasing popularity of deep learning over the past decade, stochastic gradient descent and its adaptive variants…

Optimization and Control · Mathematics 2022-01-03 Adityanarayanan Radhakrishnan , Mikhail Belkin , Caroline Uhler

We study distributed algorithms for expected loss minimization where the datasets are large and have to be stored on different machines. Often we deal with minimizing the average of a set of convex functions where each function is the…

Machine Learning · Computer Science 2019-07-24 Samira Sheikhi

A novel dynamical inertial Newton system, which is called Hessian-driven Nesterov accelerated gradient (H-NAG) flow is proposed. Convergence of the continuous trajectory are established via tailored Lyapunov function, and new first-order…

Optimization and Control · Mathematics 2019-12-25 Long Chen , Hao Luo

Variance-reduced gradient estimators for policy gradient methods have been one of the main focus of research in the reinforcement learning in recent years as they allow acceleration of the estimation process. We propose a variance-reduced…

Machine Learning · Computer Science 2023-11-28 Saber Salehkaleybar , Sadegh Khorasani , Negar Kiyavash , Niao He , Patrick Thiran