Zobrazeno 1 - 10
of 707
pro vyhledávání: '"Pokutta A"'
Autor:
Haase, Jennifer, Pokutta, Sebastian
Human-AI co-creativity represents a transformative shift in how humans and generative AI tools collaborate in creative processes. This chapter explores the synergies between human ingenuity and AI capabilities across four levels of interaction: Digit
Externí odkaz:
http://arxiv.org/abs/2411.12527
We study the problem of finding optimal sparse, manifold-aligned counterfactual explanations for classifiers. Canonically, this can be formulated as an optimization problem with multiple non-convex components, including classifier loss functions and
Externí odkaz:
http://arxiv.org/abs/2410.15723
We formalize and extend existing definitions of backdoor-based watermarks and adversarial defenses as interactive protocols between two players. The existence of these schemes is inherently tied to the learning tasks for which they are designed. Our
Externí odkaz:
http://arxiv.org/abs/2410.08864
We prove that the block-coordinate Frank-Wolfe (BCFW) algorithm converges with state-of-the-art rates in both convex and nonconvex settings under a very mild "block-iterative" assumption, newly allowing for (I) progress without activating the most-ex
Externí odkaz:
http://arxiv.org/abs/2409.06931
Grothendieck constants $K_G(d)$ bound the advantage of $d$-dimensional strategies over $1$-dimensional ones in a specific optimisation task. They have applications ranging from approximation algorithms to quantum nonlocality. However, apart from $d=2
Externí odkaz:
http://arxiv.org/abs/2409.03739
We propose the pivoting meta algorithm (PM) to enhance optimization algorithms that generate iterates as convex combinations of vertices of a feasible region $C\subseteq \mathbb{R}^n$, including Frank-Wolfe (FW) variants. PM guarantees that the activ
Externí odkaz:
http://arxiv.org/abs/2407.11760
We provide a template to derive convergence rates for the following popular versions of the Frank-Wolfe algorithm on polytopes: vanilla Frank-Wolfe, Frank-Wolfe with away steps, Frank-Wolfe with blended pairwise steps, and Frank-Wolfe with in-face di
Externí odkaz:
http://arxiv.org/abs/2406.18789
Autor:
Pauls, Jan, Zimmer, Max, Kelly, Una M., Schwartz, Martin, Saatchi, Sassan, Ciais, Philippe, Pokutta, Sebastian, Brandt, Martin, Gieseke, Fabian
We propose a framework for global-scale canopy height estimation based on satellite data. Our model leverages advanced data preprocessing techniques, resorts to a novel loss function designed to counter geolocation inaccuracies inherent in the ground
Externí odkaz:
http://arxiv.org/abs/2406.01076
We present two novel six-colorings of the Euclidean plane that avoid monochromatic pairs of points at unit distance in five colors and monochromatic pairs at another specified distance $d$ in the sixth color. Such colorings have previously been known
Externí odkaz:
http://arxiv.org/abs/2404.05509
We introduce Neural Parameter Regression (NPR), a novel framework specifically developed for learning solution operators in Partial Differential Equations (PDEs). Tailored for operator learning, this approach surpasses traditional DeepONets (Lu et al
Externí odkaz:
http://arxiv.org/abs/2403.12764