Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Dehmamy, Nima"'
Despite the advancements in learning governing differential equations from observations of dynamical systems, data-driven methods are often unaware of fundamental physical laws, such as frame invariance. As a result, these algorithms may search an un
Externí odkaz:
http://arxiv.org/abs/2405.16756
Equivariant neural networks require explicit knowledge of the symmetry group. Automatic symmetry discovery methods aim to relax this constraint and learn invariance and equivariance from data. However, existing symmetry discovery methods are limited
Externí odkaz:
http://arxiv.org/abs/2310.00105
Despite the success of equivariant neural networks in scientific applications, they require knowing the symmetry group a priori. However, it may be difficult to know which symmetry to use as an inductive bias in practice. Enforcing the wrong symmetry
Externí odkaz:
http://arxiv.org/abs/2302.00236
Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys. Yet, little is known about the theoretical origin of such valleys. We present a general framework for finding contin
Externí odkaz:
http://arxiv.org/abs/2210.17216
In mathematical optimization, second-order Newton's methods generally converge faster than first-order methods, but they require the inverse of the Hessian, hence are computationally expensive. However, we discover that on sparse graphs, graph neural
Externí odkaz:
http://arxiv.org/abs/2205.13624
Existing gradient-based optimization methods update parameters locally, in a direction that minimizes the loss function. We study a different approach, symmetry teleportation, that allows parameters to travel a large distance on the loss level set, i
Externí odkaz:
http://arxiv.org/abs/2205.10637
Existing equivariant neural networks require prior knowledge of the symmetry group and discretization for continuous groups. We propose to work with Lie algebras (infinitesimal generators) instead of Lie groups. Our model, the Lie algebra convolution
Externí odkaz:
http://arxiv.org/abs/2109.07103
Hot streaks dominate the main impact of creative careers. Despite their ubiquitous nature across a wide range of creative domains, it remains unclear if there is any regularity underlying the beginning of hot streaks. Here, we develop computational m
Externí odkaz:
http://arxiv.org/abs/2103.01256
Generation and transformation of images and videos using artificial intelligence have flourished over the past few years. Yet, there are only a few works aiming to produce creative 3D shapes, such as sculptures. Here we show a novel 3D-to-3D topology
Externí odkaz:
http://arxiv.org/abs/2007.03532
Autor:
Shah, Chintan, Dehmamy, Nima, Perra, Nicola, Chinazzi, Matteo, Barabási, Albert-László, Vespignani, Alessandro, Yu, Rose
Locating the source of an epidemic, or patient zero (P0), can provide critical insights into the infection's transmission course and allow efficient resource allocation. Existing methods use graph-theoretic centrality measures and expensive message-p
Externí odkaz:
http://arxiv.org/abs/2006.11913