Results 11 to 20 of about 787,641 (342)
Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization [PDF]
Computer Vision and Pattern Recognition, 2023 Recently, flat minima are proven to be effective for improving generalization and sharpness-aware minimization (SAM) achieves state-of-the-art performance.
Xingxuan Zhang +4 more
semanticscholar +1 more source
The Subspace Flatness Conjecture and Faster Integer Programming [PDF]
IEEE Annual Symposium on Foundations of Computer Science, 2023 In a seminal paper, Kannan and Lovász (1988) considered a quantity $\mu_{K L}(\Lambda, K)$ which denotes the best volume-based lower bound on the covering radius $\mu(\Lambda, K)$ of a convex body K with respect to a lattice $\Lambda$.
Victor Reis, Thomas Rothvoss
semanticscholar +1 more source
Measuring nonstabilizerness via multifractal flatness [PDF]
Physical Review A, 2023 Universal quantum computing requires nonstabilizer (magic) quantum states. Quantifying the nonstabilizerness and relating it to other quantum resources is vital for characterizing the complexity of quantum many-body systems. In this work, we prove that a
X. Turkeshi, M. Schirò, P. Sierant
semanticscholar +1 more source
A Comparative Study of Nonlinear MPC and Differential-Flatness-Based Control for Quadrotor Agile Flight [PDF]
IEEE Transactions on robotics, 2021 Accurate trajectory-tracking control for quadrotors is essential for safe navigation in cluttered environments. However, this is challenging in agile flights due to nonlinear dynamics, complex aerodynamic effects, and actuation constraints.
Sihao Sun +4 more
semanticscholar +1 more source
Flatness-Aware Minimization for Domain Generalization [PDF]
IEEE International Conference on Computer Vision, 2023 Domain generalization (DG) seeks to learn robust models that generalize well under unknown distribution shifts. As a critical aspect of DG, optimizer selection has not been explored in depth.
Xingxuan Zhang +5 more
semanticscholar +1 more source
Aerobatic Trajectory Generation for a VTOL Fixed-Wing Aircraft Using Differential Flatness [PDF]
IEEE Transactions on robotics, 2022 This article proposes a novel algorithm for aerobatic trajectory generation for a vertical take-off and landing (VTOL) tailsitter flying wing aircraft. The algorithm differs from existing approaches for fixed-wing trajectory generation, as it considers a
E. Tal, Gilhyun Ryou, S. Karaman
semanticscholar +1 more source
DLME: Deep Local-flatness Manifold Embedding [PDF]
European Conference on Computer Vision, 2022 Manifold learning (ML) aims to seek low-dimensional embedding from high-dimensional data. The problem is challenging on real-world datasets, especially with under-sampling data, and we find that previous methods perform poorly in this case. Generally, ML
Zelin Zang +7 more
semanticscholar +1 more source
Flat coordinates of flat Stäckel systems [PDF]
Applied Mathematics and Computation, 2015 In this article we explicitely construct transformation bewteen separable and flat coordinates for flat Stäckel systems and exploit the structre of these systems in flat coordinates. In the elliptic case these coordinates become well known generalized elliptical coordinates of Jacobi.
Krzysztof Marciniak, Maciej Blaszak
openaire +4 more sources
Proceedings of the National Academy of Sciences of the United States of America, 2021 Significance One key ingredient in deep learning is the stochastic gradient descent (SGD) algorithm, which allows neural nets to find generalizable solutions at flat minima of the high-dimensional loss function.
Yu Feng, Y. Tu
semanticscholar +1 more source
Accurate Tracking of Aggressive Quadrotor Trajectories Using Incremental Nonlinear Dynamic Inversion and Differential Flatness [PDF]
IEEE Conference on Decision and Control, 2018 In this paper, we propose a novel control law for accurate tracking of aggressive (i.e., high-speed and high-acceleration) quadcopter trajectories.
E. Tal, S. Karaman
semanticscholar +1 more source