Jointly Explicit and Implicit Cross-Modal Interaction Network for Anterior Chamber Inflammation Diagnosis

no code implementations • 11 Dec 2023 • Qian Shao, Ye Dai, Haochao Ying, Kan Xu, Jinhong Wang, Wei Chi, Jian Wu

To this end, we propose a jointly Explicit and implicit Cross-Modal Interaction Network (EiCI-Net) for Anterior Chamber Inflammation Diagnosis that uses anterior segment optical coherence tomography (AS-OCT) images, slit-lamp images, and clinical data jointly.

Clinical Knowledge Informativeness

Optimal Heterogeneous Collaborative Linear Regression and Contextual Bandits

no code implementations • 9 Jun 2023 • Xinmeng Huang, Kan Xu, Donghwan Lee, Hamed Hassani, Hamsa Bastani, Edgar Dobriban

MOLAR improves the dependence of the estimation error on the data dimension, compared to independent least squares estimates.

Multi-Armed Bandits regression

Multitask Learning and Bandits via Robust Statistics

no code implementations • 28 Dec 2021 • Kan Xu, Hamsa Bastani

Decision-makers often simultaneously face many related but heterogeneous learning problems.

Vocal Bursts Intensity Prediction

Uniformly Conservative Exploration in Reinforcement Learning

1 code implementation • 25 Oct 2021 • Wanqiao Xu, Jason Yecheng Ma, Kan Xu, Hamsa Bastani, Osbert Bastani

A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes.

reinforcement-learning Reinforcement Learning (RL)

Robust Generalization of Quadratic Neural Networks via Function Identification

no code implementations • 22 Sep 2021 • Kan Xu, Hamsa Bastani, Osbert Bastani

We study this problem from the perspective of the statistical concept of parameter identification.

Generalization Bounds Learning Theory +2

Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings

no code implementations • 18 Apr 2021 • Kan Xu, Xuanyi Zhao, Hamsa Bastani, Osbert Bastani

However, learning word embeddings from new domains with limited training data can be challenging, because the meaning/usage may be different in the new domain, e. g., the word ``positive'' typically has positive sentiment, but often has negative sentiment in medical notes since it may imply that a patient tested positive for a disease.

Generalization Bounds Learning Word Embeddings +1

Two-Stage Maximum Score Estimator

no code implementations • 7 Sep 2020 • Wayne Yuan Gao, Sheng Xu, Kan Xu

We characterize the asymptotic distribution of the TSMS estimator, which features phase transitions depending on the dimension and thus the convergence rate of the first-stage estimation.

regression Vocal Bursts Valence Prediction

WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition

no code implementations • EMNLP 2018 • Yufeng Diao, Hongfei Lin, Di wu, Liang Yang, Kan Xu, Zhihao Yang, Jian Wang, Shaowu Zhang, Bo Xu, Dongyu Zhang

In this work, we first use WordNet to understand and expand word embedding for settling the polysemy of homographic puns, and then propose a WordNet-Encoded Collocation-Attention network model (WECA) which combined with the context weights for recognizing the puns.