Zobrazeno 1 - 10
of 7 060
pro vyhledávání: '"Alex, L"'
The study of unconstrained convex optimization has historically been concerned with worst-case a priori convergence rates. The development of the Optimized Gradient Method (OGM), due to Drori and Teboulle, Kim and Fessler, marked a major milestone in
Externí odkaz:
http://arxiv.org/abs/2412.06731
Recent works by Altschuler and Parrilo and the authors have shown that it is possible to accelerate the convergence of gradient descent on smooth convex functions, even without momentum, just by picking special stepsizes. In this paper, we provide a
Externí odkaz:
http://arxiv.org/abs/2410.16249
Autor:
Yang, John, Jimenez, Carlos E., Zhang, Alex L., Lieret, Kilian, Yang, Joyce, Wu, Xindi, Press, Ori, Muennighoff, Niklas, Synnaeve, Gabriel, Narasimhan, Karthik R., Yang, Diyi, Wang, Sida I., Press, Ofir
Autonomous systems for software engineering are now capable of fixing bugs and developing features. These systems are commonly evaluated on SWE-bench (Jimenez et al., 2024a), which assesses their ability to solve software issues from GitHub repositor
Externí odkaz:
http://arxiv.org/abs/2410.03859
Drori and Teboulle [4] conjectured that the minimax optimal constant stepsize for N steps of gradient descent is given by the stepsize that balances performance on Huber and quadratic objective functions. This was numerically supported by semidefinit
Externí odkaz:
http://arxiv.org/abs/2407.11739
This work considers gradient descent for L-smooth convex optimization with stepsizes larger than the classic regime where descent can be ensured. The stepsize schedules considered are similar to but differ slightly from the recent silver stepsizes of
Externí odkaz:
http://arxiv.org/abs/2403.14045
Autor:
Wang, Alex L., Kilinc-Karzan, Fatma
Quadratically constrained quadratic programs (QCQPs) are a highly expressive class of nonconvex optimization problems. While QCQPs are NP-hard in general, they admit a natural convex relaxation via the standard semidefinite program (SDP) relaxation.
Externí odkaz:
http://arxiv.org/abs/2403.04752
An electron-positron cascade in the magnetospheres of Kerr Black Holes (BH) is a fundamental ingredient to fueling the relativistic $\gamma$-ray jets seen at the polar regions of galactic supermassive BHs (SMBH). This leptonic cascade occurs in the "
Externí odkaz:
http://arxiv.org/abs/2310.18837
Recently Grimmer [1] showed for smooth convex optimization by utilizing longer steps periodically, gradient descent's textbook $LD^2/2T$ convergence guarantees can be improved by constant factors, conjecturing an accelerated rate strictly faster than
Externí odkaz:
http://arxiv.org/abs/2309.09961