Results 11 to 20 of about 12,319,152 (351)
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 +1 more source
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 +3 more
semanticscholar +1 more source
Directly Fine-Tuning Diffusion Models on Differentiable Rewards [PDF]
International Conference on Learning Representations, 2023 We present Direct Reward Fine-Tuning (DRaFT), a simple and effective method for fine-tuning diffusion models to maximize differentiable reward functions, such as scores from human preference models.
Kevin Clark +3 more
semanticscholar +1 more source
Intermittency of Riemann’s non-differentiable function through the fourth-order flatness [PDF]
Journal of Mathematics and Physics, 2019 Riemann’s non-differentiable function is one of the most famous examples of continuous but nowhere differentiable functions, but it has also been shown to be relevant from a physical point of view.
A. Boritchev +2 more
semanticscholar +1 more source
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 +1 more source
DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing [PDF]
Computer Vision and Pattern Recognition, 2019 We propose a differentiable sphere tracing algorithm to bridge the gap between inverse graphics methods and the recently proposed deep learning based implicit signed distance function.
Shaohui Liu +5 more
semanticscholar +1 more source
Representation of a Standard Continuous Function by a Microscope [PDF]
Al-Rafidain Journal of Computer Sciences and Mathematics, 2010 The aim of this paper is to provide a representation of a standard continuous function and a standard differentiable function by mean of a microscope. More precisely, under certain conditions, the following results have been obtained.
Tahir Ismail, Hind Saleh
doaj +1 more source
IEEE Access, 2022 We present a method based on combining a smooth generalized pinball support vector machine (SVM) and variational autoencoders (VAEs) in chest X-ray (CXR) images.
Wachiraphong Ratiphaphongthon +2 more
doaj +1 more source
Soft Rasterizer: A Differentiable Renderer for Image-Based 3D Reasoning [PDF]
IEEE International Conference on Computer Vision, 2019 Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation. By inverting such renderer, one can think of a learning approach to infer 3D information from 2D images. However, standard graphics renderers
Shichen Liu +3 more
semanticscholar +1 more source
Implications of Non-Differentiable Entropy on a Space-Time Manifold
Entropy, 2015 Assuming that the motions of a complex system structural units take place on continuous, but non-differentiable curves of a space-time manifold, the scale relativity model with arbitrary constant fractal dimension (the hydrodynamic and wave function ...
Maricel Agop +3 more
doaj +1 more source