Zobrazeno 1 - 10
of 115
pro vyhledávání: '"Harris, Kameron Decker"'
Tensor completion is a core machine learning algorithm used in recommender systems and other domains with missing data. While the matrix case is well-understood, theoretical results for tensor problems are limited, particularly when the sampling patt
Externí odkaz:
http://arxiv.org/abs/2306.06262
Scientists construct connectomes, comprehensive descriptions of neuronal connections across a brain, in order to better understand and model brain function. Interactive visualizations of these pathways would enable exploratory analysis of such inform
Externí odkaz:
http://arxiv.org/abs/2205.02291
Autor:
Harris, Kameron Decker, Zhu, Yizhe
Publikováno v:
SIAM Journal on Mathematics of Data Science, 3(4), 1117-1140, 2021
We provide a novel analysis of low-rank tensor completion based on hypergraph expanders. As a proxy for rank, we minimize the max-quasinorm of the tensor, which generalizes the max-norm for matrices. Our analysis is deterministic and shows that the n
Externí odkaz:
http://arxiv.org/abs/1910.10692
Autor:
Harris, Kameron Decker
Publikováno v:
NeurIPS Real Neurons Hidden Units (NeuroAI workshop) 2019
Many biological learning systems such as the mushroom body, hippocampus, and cerebellum are built from sparsely connected networks of neurons. For a new understanding of such networks, we study the function spaces induced by sparse random features an
Externí odkaz:
http://arxiv.org/abs/1909.02603
Dynamic mode decomposition (DMD) is a data-driven method that models high-dimensional time series as a sum of spatiotemporal modes, where the temporal modes are constrained by linear dynamics. For nonlinear dynamical systems exhibiting strongly coher
Externí odkaz:
http://arxiv.org/abs/1906.05973
We present a windowed technique to learn parsimonious time-varying autoregressive models from multivariate timeseries. This unsupervised method uncovers interpretable spatiotemporal structure in data via non-smooth and non-convex optimization. In eac
Externí odkaz:
http://arxiv.org/abs/1905.08389
Recovering brain connectivity from tract tracing data is an important computational problem in the neurosciences. Mesoscopic connectome reconstruction was previously formulated as a structured matrix regression problem (Harris et al., 2016), but exis
Externí odkaz:
http://arxiv.org/abs/1808.05510
Publikováno v:
Proceedings of the National Academy of Sciences of the United States of America, 2021 May . 118(21), 1-12.
Externí odkaz:
https://www.jstor.org/stable/27040618
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Combinator. Probab. Comp. 31 (2022) 229-267
We prove an analogue of Alon's spectral gap conjecture for random bipartite, biregular graphs. We use the Ihara-Bass formula to connect the non-backtracking spectrum to that of the adjacency matrix, employing the moment method to show there exists a
Externí odkaz:
http://arxiv.org/abs/1804.07808