Zobrazeno 1 - 10
of 9 805
pro vyhledávání: '"Monod, A."'
Autor:
Micheli, Alessandro, Monod, Mélodie
This paper tackles the challenge of learning non-Markovian optimal execution strategies in dynamic financial markets. We introduce a novel actor-critic algorithm based on Deep Deterministic Policy Gradient (DDPG) to address this issue, with a focus o
Externí odkaz:
http://arxiv.org/abs/2410.13493
Acute myeloid leukaemia (AML) is a type of blood and bone marrow cancer characterized by the proliferation of abnormal clonal haematopoietic cells in the bone marrow leading to bone marrow failure. Over the course of the disease, angiogenic factors r
Externí odkaz:
http://arxiv.org/abs/2408.13685
Autor:
Monod, Nicolas
For all algebraic groups over non-Archimedean local fields, the bounded cohomology vanishes. This follows from the corresponding statement for automorphism groups of Bruhat--Tits buildings, which hinges on the solution to the flatmate conjecture rais
Externí odkaz:
http://arxiv.org/abs/2407.01709
Bounding and predicting the generalization gap of overparameterized neural networks remains a central open problem in theoretical machine learning. Neural network optimization trajectories have been proposed to possess fractal structure, leading to b
Externí odkaz:
http://arxiv.org/abs/2406.02234
We prove that the groups of orientation-preserving homeomorphisms and diffeomorphisms of $\mathbb{R}^n$ are boundedly acyclic, in all regularities. This is the first full computation of the bounded cohomology of a transformation group that is not com
Externí odkaz:
http://arxiv.org/abs/2405.20395
We propose an algebraic geometric framework to study the expressivity of linear activation neural networks. A particular quantity of neural networks that has been actively studied is the number of linear regions, which gives a quantification of the i
Externí odkaz:
http://arxiv.org/abs/2405.20174
Autor:
Talbut, Roan, Monod, Anthea
We propose a gradient descent method for solving optimisation problems arising in settings of tropical geometry - a variant of algebraic geometry that has become increasingly studied in applications such as computational biology, economics, and compu
Externí odkaz:
http://arxiv.org/abs/2405.19551
Autor:
Monod, Mélodie, Krusche, Peter, Cao, Qian, Sahiner, Berkman, Petrick, Nicholas, Ohlssen, David, Coroller, Thibaud
TorchSurv is a Python package that serves as a companion tool to perform deep survival modeling within the PyTorch environment. Unlike existing libraries that impose specific parametric forms, TorchSurv enables the use of custom PyTorch-based deep su
Externí odkaz:
http://arxiv.org/abs/2404.10761
Autor:
Wolf, Arne, Monod, Anthea
We propose a model for network community detection using topological data analysis, a branch of modern data science that leverages theory from algebraic topology to statistical analysis and machine learning. Specifically, we use cellular sheaves, whi
Externí odkaz:
http://arxiv.org/abs/2310.05767
Autor:
Wang, Qiquan, García-Redondo, Inés, Faugère, Pierre, Henselman-Petrusek, Gregory, Monod, Anthea
Publikováno v:
Computer Graphics forum, Volume 43 (2024), Number 5
Persistent homology barcodes and diagrams are a cornerstone of topological data analysis that capture the "shape" of a wide range of complex data structures, such as point clouds, networks, and functions. However, their use in statistical settings is
Externí odkaz:
http://arxiv.org/abs/2307.02904