Zobrazeno 1 - 10
of 81
pro vyhledávání: '"Nickel, Maximilian"'
Recommender systems are an important part of the modern human experience whose influence ranges from the food we eat to the news we read. Yet, there is still debate as to what extent recommendation platforms are aligned with the user goals. A core is
Externí odkaz:
http://arxiv.org/abs/2406.01611
Autor:
Liao, Danqi, Liu, Chen, Christensen, Benjamin W., Tong, Alexander, Huguet, Guillaume, Wolf, Guy, Nickel, Maximilian, Adelstein, Ian, Krishnaswamy, Smita
Publikováno v:
ICML 2023 Workshop on Topology, Algebra, and Geometry in Machine Learning
Entropy and mutual information in neural networks provide rich information on the learning process, but they have proven difficult to compute reliably in high dimensions. Indeed, in noisy and high-dimensional data, traditional estimates in ambient di
Externí odkaz:
http://arxiv.org/abs/2312.04823
Autor:
Liu, Guan-Horng, Lipman, Yaron, Nickel, Maximilian, Karrer, Brian, Theodorou, Evangelos A., Chen, Ricky T. Q.
Modern distribution matching algorithms for training diffusion or flow models directly prescribe the time evolution of the marginal distributions between two boundary distributions. In this work, we consider a generalized distribution matching setup,
Externí odkaz:
http://arxiv.org/abs/2310.02233
Autor:
Bhaskar, Dhananjay, Zhang, Yanlei, Xu, Charles, Sun, Xingzhi, Fasina, Oluwadamilola, Wolf, Guy, Nickel, Maximilian, Perlmutter, Michael, Krishnaswamy, Smita
In this paper we introduce DYMAG: a message passing paradigm for GNNs built on the expressive power of continuous, multiscale graph-dynamics. Standard discrete-time message passing algorithms implicitly make use of simplistic graph dynamics and aggre
Externí odkaz:
http://arxiv.org/abs/2309.09924
The expressive power of graph neural networks is usually measured by comparing how many pairs of graphs or nodes an architecture can possibly distinguish as non-isomorphic to those distinguishable by the $k$-dimensional Weisfeiler-Leman ($k$-WL) test
Externí odkaz:
http://arxiv.org/abs/2307.05775
Recent successful generative models are trained by fitting a neural network to an a-priori defined tractable probability density path taking noise to training examples. In this paper we investigate the space of Gaussian probability paths, which inclu
Externí odkaz:
http://arxiv.org/abs/2306.06626
Autor:
Fasina, Oluwadamilola, Huguet, Guillaume, Tong, Alexander, Zhang, Yanlei, Wolf, Guy, Nickel, Maximilian, Adelstein, Ian, Krishnaswamy, Smita
Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the underlying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature. To
Externí odkaz:
http://arxiv.org/abs/2306.06062
Group fairness is a popular approach to prevent unfavorable treatment of individuals based on sensitive attributes such as race, gender, and disability. However, the reliance of group fairness on access to discrete group information raises several li
Externí odkaz:
http://arxiv.org/abs/2305.11361
Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept "dog" entails all images that contain dogs. Despite being intuitive, current large-scale vision and language models such as CLIP do not explicitly ca
Externí odkaz:
http://arxiv.org/abs/2304.09172
Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep sequence models have costs that scale with the sequence length rather t
Externí odkaz:
http://arxiv.org/abs/2212.13659