Search Results for author: Qian Lin

Found 35 papers, 11 papers with code

Improved Word Sense Disambiguation with Enhanced Sense Representations

1 code implementation Findings (EMNLP) 2021 Yang song, Xin Cai Ong, Hwee Tou Ng, Qian Lin

Current state-of-the-art supervised word sense disambiguation (WSD) systems (such as GlossBERT and bi-encoder model) yield surprisingly good results by purely leveraging pre-trained language models and short dictionary definitions (or glosses) of the different word senses.

Word Sense Disambiguation

On the Saturation Effect of Kernel Ridge Regression

no code implementations15 May 2024 Yicheng Li, Haobo Zhang, Qian Lin

The saturation effect refers to the phenomenon that the kernel ridge regression (KRR) fails to achieve the information theoretical lower bound when the smoothness of the underground truth function exceeds certain level.


The phase diagram of kernel interpolation in large dimensions

no code implementations19 Apr 2024 Haobo Zhang, Weihao Lu, Qian Lin

The generalization ability of kernel interpolation in large dimensions (i. e., $n \asymp d^{\gamma}$ for some $\gamma>0$) might be one of the most interesting problems in the recent renaissance of kernel regression, since it may help us understand the 'benign overfitting phenomenon' reported in the neural networks literature.

The Optimality of Kernel Classifiers in Sobolev Space

no code implementations2 Feb 2024 Jianfa Lai, Zhifan Li, Dongming Huang, Qian Lin

Kernel methods are widely used in machine learning, especially for classification problems.


Off-Policy Primal-Dual Safe Reinforcement Learning

2 code implementations26 Jan 2024 Zifan Wu, Bo Tang, Qian Lin, Chao Yu, Shangqin Mao, Qianlong Xie, Xingxing Wang, Dong Wang

Results on benchmark tasks show that our method not only achieves an asymptotic performance comparable to state-of-the-art on-policy methods while using much fewer samples, but also significantly reduces constraint violation during training.

reinforcement-learning Safe Reinforcement Learning

Policy-regularized Offline Multi-objective Reinforcement Learning

1 code implementation4 Jan 2024 Qian Lin, Chao Yu, Zongkai Liu, Zifan Wu

In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL.

Multi-Objective Reinforcement Learning Offline RL +1

Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay

no code implementations3 Jan 2024 Yicheng Li, Weiye Gan, Zuoqiang Shi, Qian Lin

The generalization error curve of certain kernel regression method aims at determining the exact order of generalization error with various source condition, noise level and choice of the regularization parameter rather than the minimax rate.


Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions

no code implementations2 Jan 2024 Haobo Zhang, Yicheng Li, Weihao Lu, Qian Lin

Motivated by the studies of neural networks (e. g., the neural tangent kernel theory), we perform a study on the large-dimensional behavior of kernel ridge regression (KRR) where the sample size $n \asymp d^{\gamma}$ for some $\gamma > 0$.


Optimal Rate of Kernel Regression in Large Dimensions

no code implementations8 Sep 2023 Weihao Lu, Haobo Zhang, Yicheng Li, Manyun Xu, Qian Lin

We perform a study on kernel regression for large-dimensional data (where the sample size $n$ is polynomially depending on the dimension $d$ of the samples, i. e., $n\asymp d^{\gamma}$ for some $\gamma >0$ ).


Safe Offline Reinforcement Learning with Real-Time Budget Constraints

1 code implementation1 Jun 2023 Qian Lin, Bo Tang, Zifan Wu, Chao Yu, Shangqin Mao, Qianlong Xie, Xingxing Wang, Dong Wang

Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years.

reinforcement-learning Reinforcement Learning (RL)

Generalization Ability of Wide Residual Networks

no code implementations29 May 2023 Jianfa Lai, Zixiong Yu, Songtao Tian, Qian Lin

This uniform convergence further guarantees that the generalization error of the residual network converges to that of the kernel regression with respect to the RNTK.


On the Optimality of Misspecified Kernel Ridge Regression

no code implementations12 May 2023 Haobo Zhang, Yicheng Li, Weihao Lu, Qian Lin

In the misspecified kernel ridge regression problem, researchers usually assume the underground true function $f_{\rho}^{*} \in [\mathcal{H}]^{s}$, a less-smooth interpolation space of a reproducing kernel Hilbert space (RKHS) $\mathcal{H}$ for some $s\in (0, 1)$.


On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains

no code implementations4 May 2023 Yicheng Li, Zixiong Yu, Guhan Chen, Qian Lin

In this paper, we provide a strategy to determine the eigenvalue decay rate (EDR) of a large class of kernel functions defined on a general domain rather than $\mathbb S^{d}$.


Kernel interpolation generalizes poorly

no code implementations28 Mar 2023 Yicheng Li, Haobo Zhang, Qian Lin

One of the most interesting problems in the recent renaissance of the studies in kernel regression might be whether the kernel interpolation can generalize well, since it may help us understand the `benign overfitting henomenon' reported in the literature on deep networks.


Generalization Ability of Wide Neural Networks on $\mathbb{R}$

no code implementations12 Feb 2023 Jianfa Lai, Manyun Xu, Rui Chen, Qian Lin

We perform a study on the generalization ability of the wide two-layer ReLU neural network on $\mathbb{R}$.

A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues

1 code implementation22 Feb 2022 Qian Lin, Hwee Tou Ng

We leverage unlabeled data to improve classification in student training where we employ two teachers to refine the labeling of unlabeled data through teacher-student learning in a bootstrapping manner.

Data Augmentation

A Co-Attentive Cross-Lingual Neural Model for Dialogue Breakdown Detection

1 code implementation COLING 2020 Qian Lin, Souvik Kundu, Hwee Tou Ng

One of the major challenges is that a dialogue system may generate an undesired utterance leading to a dialogue breakdown, which degrades the overall interaction quality.

Language Modelling Word Embeddings

Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution

no code implementations18 Oct 2020 Xiaoyu Xiang, Qian Lin, Jan P. Allebach

In this paper, we aim to generate an artifact-free high-resolution image from a low-resolution one compressed with an arbitrary quality factor by exploring joint compression artifacts reduction (CAR) and super-resolution (SR) tasks.

Face Detection Optical Character Recognition +3

MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines

no code implementations17 Oct 2020 Zhaojing Luo, Sai Ho Yeung, Meihui Zhang, Kaiping Zheng, Lei Zhu, Gang Chen, Feiyi Fan, Qian Lin, Kee Yuan Ngiam, Beng Chin Ooi

In this paper, we identify two main challenges that arise during the deployment of machine learning pipelines, and address them with the design of versioning for an end-to-end analytics system MLCask.

BIG-bench Machine Learning Management

The Blessing and the Curse of the Noise behind Facial Landmark Annotations

no code implementations30 Jul 2020 Xiaoyu Xiang, Yang Cheng, Shaoyuan Xu, Qian Lin, Jan Allebach

The evolving algorithms for 2D facial landmark detection empower people to recognize faces, analyze facial expressions, etc.

Face Alignment Facial Landmark Detection

Learning to Identify Follow-Up Questions in Conversational Question Answering

no code implementations ACL 2020 Souvik Kundu, Qian Lin, Hwee Tou Ng

Despite recent progress in conversational question answering, most prior work does not focus on follow-up questions.

Conversational Question Answering

LoCEC: Local Community-based Edge Classification in Large Online Social Networks

no code implementations11 Feb 2020 Chonggang Song, Qian Lin, Guohui Ling, Zongyi Zhang, Hongzhao Chen, Jun Liao, Chuan Chen

To tackle the challenges, we propose a Local Community-based Edge Classification (LoCEC) framework that classifies user relationships in a social network into real-world social connection types.

Classification Edge Classification +2

Print Defect Mapping with Semantic Segmentation

no code implementations27 Jan 2020 Augusto C. Valente, Cristina Wada, Deangela Neves, Deangeli Neves, Fábio V. M. Perez, Guilherme A. S. Megeto, Marcos H. Cascone, Otavio Gomes, Qian Lin

Efficient automated print defect mapping is valuable to the printing industry since such defects directly influence customer-perceived printer quality and manually mapping them is cost-ineffective.

Feature Engineering Segmentation +1

Multi-View Matching Network for 6D Pose Estimation

no code implementations27 Nov 2019 Daniel Mas Montserrat, Jianhang Chen, Qian Lin, Jan P. Allebach, Edward J. Delp

Applications that interact with the real world such as augmented reality or robot manipulation require a good understanding of the location and pose of the surrounding objects.

6D Pose Estimation object-detection +2

Blockchains vs. Distributed Databases: Dichotomy and Fusion

1 code implementation3 Oct 2019 Pingcheng Ruan, Gang Chen, Tien Tuan Anh Dinh, Qian Lin, Dumitrel Loghin, Beng Chin Ooi, Meihui Zhang

As blockchain evolves into another data management system, the natural question is how it compares against distributed database systems.

Databases Performance

The Disruptions of 5G on Data-driven Technologies and Applications

no code implementations6 Sep 2019 Dumitrel Loghin, Shaofeng Cai, Gang Chen, Tien Tuan Anh Dinh, Feiyi Fan, Qian Lin, Janice Ng, Beng Chin Ooi, Xutao Sun, Quang-Trung Ta, Wei Wang, Xiaokui Xiao, Yang Yang, Meihui Zhang, Zhonghua Zhang

With 5G on the verge of being adopted as the next mobile network, there is a need to analyze its impact on the landscape of computing and data management.

Networking and Internet Architecture Databases Distributed, Parallel, and Cluster Computing

Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks

3 code implementations EMNLP 2018 Biao Zhang, Deyi Xiong, Jinsong Su, Qian Lin, Huiji Zhang

Experiments on WMT14 translation tasks demonstrate that ATR-based neural machine translation can yield competitive performance on English- German and English-French language pairs in terms of both translation quality and speed.

Chinese Word Segmentation Machine Translation +2

Otem&Utem: Over- and Under-Translation Evaluation Metric for NMT

1 code implementation24 Jul 2018 Jing Yang, Biao Zhang, Yue Qin, Xiangwen Zhang, Qian Lin, Jinsong Su

Although neural machine translation(NMT) yields promising translation performance, it unfortunately suffers from over- and under-translation is- sues [Tu et al., 2016], of which studies have become research hotspots in NMT.

Machine Translation NMT +1

Towards Scaling Blockchain Systems via Sharding

3 code implementations2 Apr 2018 Hung Dang, Tien Tuan Anh Dinh, Dumitrel Loghin, Ee-Chien Chang, Qian Lin, Beng Chin Ooi

In this work, we take a principled approach to apply sharding, which is a well-studied and proven technique to scale out databases, to blockchain systems in order to improve their transaction throughput at scale.

Distributed, Parallel, and Cluster Computing Cryptography and Security Databases

ForkBase: An Efficient Storage Engine for Blockchain and Forkable Applications

no code implementations14 Feb 2018 Sheng Wang, Tien Tuan Anh Dinh, Qian Lin, Zhongle Xie, Meihui Zhang, Qingchao Cai, Gang Chen, Wanzeng Fu, Beng Chin Ooi, Pingcheng Ruan

By integrating the core application properties into the storage, ForkBase not only delivers high performance but also reduces development effort.

Databases Cryptography and Security Distributed, Parallel, and Cluster Computing

Signed Support Recovery for Single Index Models in High-Dimensions

no code implementations7 Nov 2015 Matey Neykov, Qian Lin, Jun S. Liu

When $s=O(p^{1-\delta})$ for some $\delta>0$, we demonstrate that both procedures can succeed in recovering the support of $\boldsymbol{\beta}$ as long as the rescaled sample size $\kappa=\frac{n}{s\log(p-s)}$ is larger than a certain critical threshold.

Vocal Bursts Intensity Prediction

Dynamic indifference pricing via the G-expectation

no code implementations30 Mar 2015 Qian Lin

We study the dynamic indifference pricing with ambiguity preferences.

Cannot find the paper you are looking for? You can Submit a new open access paper.