Zobrazeno 1 - 10
of 6 081
pro vyhledávání: '"Vandermeulen"'
We show that deep neural networks achieve dimension-independent rates of convergence for learning structured densities such as those arising in image, audio, video, and text applications. More precisely, we demonstrate that neural networks with a sim
Externí odkaz:
http://arxiv.org/abs/2411.15095
We consider the problem of estimating a structured multivariate density, subject to Markov conditions implied by an undirected graph. In the worst case, without Markovian assumptions, this problem suffers from the curse of dimensionality. Our main re
Externí odkaz:
http://arxiv.org/abs/2410.07685
In this paper we discuss gauging noninvertible zero-form symmetries in two dimensions, extending our previous work. Specifically, in this work we discuss more general gauged noninvertible symmetries in which the noninvertible symmetry is not multipli
Externí odkaz:
http://arxiv.org/abs/2408.16811
The increase in high-dimensional multiomics data demands advanced integration models to capture the complexity of human diseases. Graph-based deep learning integration models, despite their promise, struggle with small patient cohorts and high-dimens
Externí odkaz:
http://arxiv.org/abs/2408.02845
Autor:
Robbins, Daniel, Vandermeulen, Thomas
We define a Frobenius algebra over fusion categories of the form Rep$(G)\boxtimes$Rep$(G)$ which generalizes the diagonal subgroup of $G\times G$. This allows us to extend field theoretical constructions which depend on the existence of a diagonal su
Externí odkaz:
http://arxiv.org/abs/2405.08058
Publikováno v:
JHEP 02 (2024) 154
In this paper we discuss gauging noninvertible zero-form symmetries in two dimensions. We specialize to certain gaugeable cases, specifically, fusion categories of the form Rep(H) for H a suitable Hopf algebra (which includes the special case Rep(G)
Externí odkaz:
http://arxiv.org/abs/2311.16230
Autor:
Vandermeulen, Thomas
Gauging a symmetry can be thought of as the insertion of a spacetime-filling defect. Accordingly, we regard each gaugeable symmetry in a theory as defining a $-1$-form symmetry via condensation. The resulting operators, called gauge defects, have a n
Externí odkaz:
http://arxiv.org/abs/2310.08626
Autor:
Vandermeulen, Thomas
Symmetry Protected Topological (SPT) phases describe trivially-acting symmetries. We argue that a symmetry-based description of SPT phases ought to include the topological twist fields associated to the symmetry. Doing so allows us to predict the res
Externí odkaz:
http://arxiv.org/abs/2308.10082
Autor:
Muttenthaler, Lukas, Vandermeulen, Robert A., Zhang, Qiuyi, Unterthiner, Thomas, Müller, Klaus-Robert
Model overconfidence and poor calibration are common in machine learning and difficult to account for when applying standard empirical risk minimization. In this work, we propose a novel method to alleviate these problems that we call odd-$k$-out lea
Externí odkaz:
http://arxiv.org/abs/2307.02245