no code implementations • 23 Apr 2024 • Tuoyi Zhao, Wen-Xin Zhou, Lan Wang
By leveraging the structure of the newsvendor problem, we attain a faster excess population risk bound compared to that obtained from an indiscriminate application of existing results for general nonsmooth convex loss.
no code implementations • 22 Mar 2024 • Sepehr Dehdashtian, Lan Wang, Vishnu Naresh Boddeti
However, owing to the nature of their training process, these models have the potential to 1) propagate or amplify societal biases in the training data and 2) learn to rely on spurious features.
no code implementations • 11 Mar 2024 • Lan Wang, Vishnu Boddeti, SerNam Lim
While existing video editing tasks are limited to changes in attributes, backgrounds, and styles, our method aims to predict open-ended human action changes in video.
no code implementations • 9 Mar 2024 • Yudong Yang, Rongfeng Su, Xiaokang Liu, Nan Yan, Lan Wang
In this model, the inherent acoustic characteristics of individuals related to the tongue motion details are encoded by using wav2vec 2. 0, while the ASR transcriptions related to the universality of tongue motions are encoded by using BERT.
no code implementations • 14 Jun 2023 • Zeyu Bian, Chengchun Shi, Zhengling Qi, Lan Wang
This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated.
no code implementations • 13 Jun 2023 • Lan Wang, Ruiling He, Lili Zhao, Jia Wang, Zhengzi Geng, Tao Ren, Guo Zhang, Peng Zhang, Kaiqiang Tang, Chaofei Gao, Fei Chen, Liting Zhang, Yonghe Zhou, Xin Li, Fanbin He, Hui Huan, Wenjuan Wang, Yunxiao Liang, Juan Tang, Fang Ai, Tingyu Wang, Liyun Zheng, Zhongwei Zhao, Jiansong Ji, Wei Liu, Jiaojiao Xu, Bo Liu, Xuemei Wang, Yao Zhang, Qiong Yan, Muhan Lv, Xiaomei Chen, Shuhua Zhang, Yihua Wang, Yang Liu, Li Yin, Yanni Liu, Yanqing Huang, Yunfang Liu, Kun Wang, Meiqin Su, Li Bian, Ping An, Xin Zhang, Linxue Qian, Shao Li, Xiaolong Qi
Validation analysis revealed that the AUCs of DLRP were 0. 91 for GEV (95% CI 0. 90 to 0. 93, p < 0. 05) and 0. 88 for HRV (95% CI 0. 86 to 0. 89, p < 0. 01), which were significantly and robustly better than canonical risk indicators, including the value of LSM and SSM.
no code implementations • 15 Apr 2023 • Kwei-Herng Lai, Lan Wang, Huiyuan Chen, Kaixiong Zhou, Fei Wang, Hao Yang, Xia Hu
We formulate context sampling into the Markov decision process and exploit deep reinforcement learning to optimize the time series domain adaptation process via context sampling and design a tailored reward function to generate domain-invariant features that better align two domains for anomaly detection.
no code implementations • CVPR 2023 • Lan Wang, Gaurav Mittal, Sandra Sajeev, Ye Yu, Matthew Hall, Vishnu Naresh Boddeti, Mei Chen
We present ProTeGe as the first method to perform VTG-based untrimmed pretraining to bridge the gap between trimmed pretrained backbones and downstream VTG tasks.
no code implementations • 29 Dec 2022 • Yang Xu, Chengchun Shi, Shikai Luo, Lan Wang, Rui Song
Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy.
no code implementations • 23 Dec 2022 • Zuyue Fu, Zhengling Qi, Zhuoran Yang, Zhaoran Wang, Lan Wang
To tackle the distributional mismatch, we leverage the idea of pessimism and use our OPE method to develop an off-policy learning algorithm for finding a desirable policy pair for both Alice and Bob.
no code implementations • 8 Dec 2022 • Huiyuan Chen, Yusan Lin, Menghai Pan, Lan Wang, Chin-Chia Michael Yeh, Xiaoting Li, Yan Zheng, Fei Wang, Hao Yang
Transformer-based sequential recommenders are very powerful for capturing both short-term and long-term sequential item dependencies.
1 code implementation • CVPR 2022 • Lan Wang, Vishnu Naresh Boddeti
Second, we apply NCINet to identify the causal relations between image representations of different pairs of attributes with known and unknown causal relations between the labels.
no code implementations • 4 Mar 2022 • Olukunle O. Owolabi, Kathryn Lawson, Sanhita Sengupta, Yingsi Huang, Lan Wang, Chaopeng Shen, Mila Getmansky Sherman, Deborah A. Sunter
Hydroelectric power (hydropower) is unique in that it can function as both a conventional source of electricity and as backup storage (pumped hydroelectric storage) for providing energy in times of high demand on the grid.
no code implementations • 24 Jan 2022 • Xurong Xie, Xiang Sui, Xunying Liu, Lan Wang
Meanwhile, approaches of multi-accent modelling including multi-style training, multi-accent decision tree state tying, DNN tandem and multi-level adaptive network (MLAN) tandem hidden Markov model (HMM) modelling are combined and compared in this paper.
no code implementations • 24 Jan 2022 • Xurong Xie, Rukiye Ruzi, Xunying Liu, Lan Wang
Dysarthric speech recognition is a challenging task due to acoustic variability and limited amount of available data.
no code implementations • 13 Jan 2022 • Lan Wang, Yusan Lin, Yuhang Wu, Huiyuan Chen, Fei Wang, Hao Yang
Today's cyber-world is vastly multivariate.
1 code implementation • 22 Dec 2021 • Mei-Ling E. Feng, Olukunle O. Owolabi, Toryn L. J. Schafer, Sanhita Sengupta, Lan Wang, David S. Matteson, Judy P. Che-Castaldo, Deborah A. Sunter
These flexible, species-specific estimates can allow future animal-indicators of grid reliability to be investigated in more diverse regions and ecological communities, providing a better understanding of the variation that exists in animal-outage relationship.
no code implementations • 10 Nov 2021 • Olukunle O. Owolabi, Toryn L. J. Schafer, Georgia E. Smits, Sanhita Sengupta, Sean E. Ryan, Lan Wang, David S. Matteson, Mila Getmansky Sherman, Deborah A. Sunter
After correcting for temporal effects, we found an increase in VRE penetration is associated with decrease in system electricity price in all ISOs studied.
1 code implementation • 7 Oct 2021 • Jin Li, Haibin Liu, Nan Yan, Lan Wang
Symbolic melodies generation is one of the essential tasks for automatic music generation.
1 code implementation • 12 Sep 2021 • Bashir Sadeghi, Lan Wang, Vishnu Naresh Boddeti
Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time.
1 code implementation • 19 Aug 2021 • Jin Li, Nan Yan, Lan Wang
However, cross-lingual SER remains a challenge in real-world applications due to a great difference between the source and target domain distributions.
no code implementations • 18 Aug 2021 • Jin Li, Rongfeng Su, Xurong Xie, Nan Yan, Lan Wang
The shallow stream is used to acquire traditional shallow features that is beneficial for the classification of phones or words while the deep stream is used to obtain utterance-level speaker-invariant deep features for improving the feature diversity.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 18 Aug 2021 • Jin Li, Nan Yan, Lan Wang
For example, RawNet and RawNet2 extracted speaker's feature embeddings from waveforms automatically for recognizing their voice, which can vastly reduce the front-end computation and obtain state-of-the-art performance.
no code implementations • 15 Aug 2021 • Yuhang Wu, Mengting Gu, Lan Wang, Yusan Lin, Fei Wang, Hao Yang
Modeling inter-dependencies between time-series is the key to achieve high performance in anomaly detection for multivariate time-series data.
no code implementations • ICLR 2021 • Daniel Hsu, Ziwei Ji, Matus Telgarsky, Lan Wang
This paper theoretically investigates the following empirical phenomenon: given a high-complexity network with poor generalization bounds, one can distill it into a network with nearly identical predictions but low complexity and vastly smaller generalization bounds.
1 code implementation • 19 Jan 2021 • Judy P. Che-Castaldo, Rémi Cousin, Stefani Daryanto, Grace Deng, Mei-Ling E. Feng, Rajesh K. Gupta, Dezhi Hong, Ryan M. McGranaghan, Olukunle O. Owolabi, Tianyi Qu, Wei Ren, Toryn L. J. Schafer, Ashutosh Sharma, Chaopeng Shen, Mila Getmansky Sherman, Deborah A. Sunter, Lan Wang, David S. Matteson
We also provide relevant critical risk indicators (CRIs) across diverse domains that may influence electric power grid risks, including climate, ecology, hydrology, finance, space weather, and agriculture.
Applications
1 code implementation • 14 Dec 2020 • Xurong Xie, Xunying Liu, Tan Lee, Lan Wang
A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences.
no code implementations • 4 Nov 2020 • Chenpeng Du, Hao Li, Yizhou Lu, Lan Wang, Yanmin Qian
Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 25 Nov 2019 • Yunan Wu, Lan Wang
We first study a smoothed robust estimator that directly targets the parameter corresponding to the Bayes decision rule for optimal treatment regimes estimation.
no code implementations • 10 Aug 2019 • Yunan Wu, Lan Wang
Penalized (or regularized) regression, as represented by Lasso and its variants, has become a standard technique for analyzing high-dimensional data when the number of variables substantially exceeds the sample size.
no code implementations • ECCV 2018 • Lan Wang, Chenqiang Gao, Luyu Yang, Yue Zhao, WangMeng Zuo, Deyu Meng
As a result, using partial data channels to build a full representation of multi-modalities is clearly desired.
no code implementations • 7 Mar 2016 • Lan Wang, Chenqiang Gao, Jiang Liu, Deyu Meng
Detecting complex events in a large video collection crawled from video websites is a challenging task.