paper-with-me

홈 › Papers

Whiplash Gradient Descent Dynamics

2022-03-04 · Subhransu S. Bhattacharjee, Ian R. Petersen

In this paper, we propose the Whiplash Inertial Gradient dynamics, a closed-loop optimization method that utilises gradient information, to find the minima of a cost function in finite-dimensional settings. We introduce the symplectic asymptotic convergence analysis for the Whiplash system for convex functions. We also introduce relaxation sequences to explain the non-classical nature of the algorithm and an exploring heuristic variant of the Whiplash algorithm to escape saddle points, deterministically. We study the algorithm's performance for various costs and provide a practical methodology for analyzing convergence rates using integral constraint bounds and a novel Lyapunov rate method. Our results demonstrate polynomial and exponential rates of convergence for quadratic cost functions.

📄 PDF Abstract BibTeX arXiv:2203.02140

Code (1)

SubhransuSekharBhattacharjee-01/Whiplash 공식 구현

Similar Papers 제목 키워드 기반

Curl Descent: Non-Gradient Learning Dynamics with Sign-Diverse Plasticity

2025-10-03 · Hugo Ninou, Jonathan Kadmon, N. Alex Cayco-Gajic arxiv

Gradient-based algorithms are a cornerstone of artificial neural network training, yet it remains unclear whether biological neural networks use similar gradient-based strategies during learning. Experiments often discov…

Curvature-corrected learning dynamics in deep neural networks

2020-01-01 · ICML 2020 1 · Dongsung Huh

Deep neural networks exhibit highly non-convex loss landscape, which results in complex learning dynamics under steepest gradient descent. Second order optimization methods, such as natural gradient descent, can facilita…

Second-order methods

A Mirror Descent Perspective of Smoothed Sign Descent

2024-10-18 · Shuyang Wang, Diego Klabjan

Recent work by Woodworth et al. (2020) shows that the optimization dynamics of gradient descent for overparameterized problems can be viewed as low-dimensional dual dynamics induced by a mirror map, explaining the implic…

Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent

2023-02-14 · Benjamin Gess, Sebastian Kassing, Vitalii Konarovskyi

We propose new limiting dynamics for stochastic gradient descent in the small learning rate regime called stochastic modified flows. These SDEs are driven by a cylindrical Brownian motion and improve the so-called stocha…

Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression

2024-06-06 · Jackie Lok, Rishi Sonthalia, Elizaveta Rebrova

We study the discrete dynamics of mini-batch gradient descent with random reshuffling for least squares regression. We show that the training and generalization errors depend on a sample cross-covariance matrix $Z$ betwe…

regression