Results 11 to 20 of about 13,863,270 (332)

Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient [PDF]

arXiv.org, 2022
Offline reinforcement learning, which aims at optimizing sequential decision-making strategies with historical data, has been extensively applied in real-life applications. State-Of-The-Art algorithms usually leverage powerful function approximators (e.g.
Ming Yin, Mengdi Wang, Yu-Xiang Wang
semanticscholar   +3 more sources

Some geometric properties of Riemann's non-differentiable function [PDF]

Comptes rendus. Mathematique, 2019
Riemann's non-differentiable function is a celebrated example of a continuous but almost nowhere differentiable function. There is strong numeric evidence that one of its complex versions represents a geometric trajectory in experiments related to the ...
Daniel Eceizabarrena
semanticscholar   +3 more sources

Geometric differentiability of Riemann's non-differentiable function [PDF]

Advances in Mathematics, 2019
Riemann's non-differentiable function is a classic example of a continuous function which is almost nowhere differentiable, and many results concerning its analytic regularity have been shown so far.
Daniel Eceizabarrena
semanticscholar   +3 more sources

On the Hausdorff dimension of Riemann’s non-differentiable function [PDF]

Transactions of the American Mathematical Society, 2019
Recent findings show that the classical Riemann's non-differentiable function has a physical and geometric nature as the irregular trajectory of a polygonal vortex filament driven by the binormal flow.
Daniel Eceizabarrena
semanticscholar   +3 more sources

A novel parameter-free differentiable filled function for global optimization [PDF]

Scientific Reports
The filled function method is a prominent approach in global optimization, effectively overcoming the limitations of non-global minimizers by successively locating improved local minima. While its implementation is relatively straightforward, algorithmic
Guolin Chen
doaj   +2 more sources

Variable Metric Forward–Backward Algorithm for Minimizing the Sum of a Differentiable Function and a Convex Function

Journal of Optimization Theory and Applications, 2013
International audienceWe consider the minimization of a function $G$ defined on $R^N$, which is the sum of a (non necessarily convex) differentiable function and a (non necessarily differentiable) convex function.
É. Chouzenoux, J. Pesquet, A. Repetti
semanticscholar   +3 more sources

A note on the Chebyshev coefficients of the moments of the general order derivative of an infinitely differentiable function

, 1988
An expression for the Chebyshev coefficients of the moments of the general order derivative of an infinitely differentiable function in terms of its Chebyshev coefficients is ...
A. Karageorghis
semanticscholar   +2 more sources

Differentiation of Zygmund functions [PDF]

Proceedings of the American Mathematical Society, 1993
The "little- o o Zygmund class"
David C. Ullrich
openaire   +2 more sources

The ultraspherical coefficients of the moments of a general-order derivative of an infinitely differentiable function

, 1998
A formula for the ultraspherical coefficients of the moments of one single ultraspherical polynomial of certain degree is given. Formulae for the ultraspherical coefficients of the moments of a general-order derivative of an infinitely differentiable ...
E. H. Doha
semanticscholar   +2 more sources

Differentiable Integrated Motion Prediction and Planning With Learnable Cost Function for Autonomous Driving [PDF]

IEEE Transactions on Neural Networks and Learning Systems, 2022
Predicting the future states of surrounding traffic participants and planning a safe, smooth, and socially compliant trajectory accordingly are crucial for autonomous vehicles (AVs).
Zhiyu Huang, Haochen Liu, Jingda Wu, Chen Lv   +3 more
semanticscholar   +1 more source