Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Dong, Yihe"'
Autor:
Dong, Yihe
With the rise of language and multimodal models of ever-increasing size, pretraining a general-purpose foundational model and adapting it to downstream tasks has become common practice. To this end, adaptation efficiency can be a critical bottleneck
Externí odkaz:
http://arxiv.org/abs/2408.09015
Feature engineering has demonstrated substantial utility for many machine learning workflows, such as in the small data regime or when distribution shifts are severe. Thus automating this capability can relieve much manual effort and improve model pe
Externí odkaz:
http://arxiv.org/abs/2406.04153
Estimation of temporal counterfactual outcomes from observed history is crucial for decision-making in many domains such as healthcare and e-commerce, particularly when randomized controlled trials (RCTs) suffer from high cost or impracticality. For
Externí odkaz:
http://arxiv.org/abs/2311.00886
Multimodal large-scale pretraining has shown impressive performance for unstructured data such as language and image. However, a prevalent real-world scenario involves structured data types, tabular and time-series, along with unstructured data. Such
Externí odkaz:
http://arxiv.org/abs/2305.16556
Autor:
Dong, Yihe, Arik, Sercan O.
Feature selection has been widely used to alleviate compute requirements during training, elucidate model interpretability, and improve model generalizability. We propose SLM -- Sparse Learnable Masks -- a canonical approach for end-to-end feature se
Externí odkaz:
http://arxiv.org/abs/2304.03202
Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs). In this paper, we propose a novel deep sequence model based on t
Externí odkaz:
http://arxiv.org/abs/2210.03675
Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their output can
Externí odkaz:
http://arxiv.org/abs/2103.03404
Publikováno v:
Graph Representation Learning and Beyond Workshop at ICML 2020
Hypergraphs provide a natural representation for many real world datasets. We propose a novel framework, HNHN, for hypergraph representation learning. HNHN is a hypergraph convolution network with nonlinear activation functions applied to both hypern
Externí odkaz:
http://arxiv.org/abs/2006.12278
We present simple differentially private estimators for the mean and covariance of multivariate sub-Gaussian data that are accurate at small sample sizes. We demonstrate the effectiveness of our algorithms both theoretically and empirically using syn
Externí odkaz:
http://arxiv.org/abs/2006.06618
Publikováno v:
Optimal Transport & Machine learning Workshop at NeurIPS 2019
We investigate the problem of efficiently computing optimal transport (OT) distances, which is equivalent to the node-capacitated minimum cost maximum flow problem in a bipartite graph. We compare runtimes in computing OT distances on data from sever
Externí odkaz:
http://arxiv.org/abs/2005.01182