Search Results for author: Na Li

Found 61 papers, 12 papers with code

Towards Carbon-Free Electricity: A Comprehensive Flow-Based Framework for Power Grid Carbon Accounting and Decarbonization

no code implementations7 Aug 2023 Xin Chen, Hungpo Chao, Wenbo Shi, Na Li

This paper presents a comprehensive framework for advancing research and policy development related to decarbonization in electric power systems.

Decision Making Fairness

Regularized Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity

no code implementations20 Jun 2023 Runyu Zhang, Yang Hu, Na Li

This paper focuses on reinforcement learning for the regularized robust Markov decision process (MDP) problem, an extension of the robust MDP framework.

Non-asymptotic System Identification for Linear Systems with Nonlinear Policies

no code implementations17 Jun 2023 YingYing Li, Tianpeng Zhang, Subhro Das, Jeff Shamma, Na Li

This paper considers a single-trajectory system identification problem for linear systems under general nonlinear and/or time-varying policies with i. i. d.

Ultra-Fine Entity Typing with Prior Knowledge about Labels: A Simple Clustering Based Strategy

no code implementations22 May 2023 Na Li, Zied Bouraoui, Steven Schockaert

In this paper, we show that the performance of existing methods can be improved using a simple technique: we use pre-trained label embeddings to cluster the labels into semantic domains and then treat these domains as additional types.

Entity Typing

Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Models

1 code implementation16 May 2023 Na Li, Hanane Kteich, Zied Bouraoui, Steven Schockaert

Second, concept embeddings should capture the semantic properties of concepts, whereas contextualised word vectors are also affected by other factors.

Contrastive Learning Word Embeddings

Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding

no code implementations8 Apr 2023 Tongzheng Ren, Zhaolin Ren, Na Li, Bo Dai

Optimal control is notoriously difficult for stochastic nonlinear systems.

Decentralized Riemannian natural gradient methods with Kronecker-product approximations

no code implementations16 Mar 2023 Jiang Hu, Kangkang Deng, Na Li, Quanzheng Li

With a computationally efficient approximation of the second-order information, natural gradient methods have been successful in solving large-scale structured optimization problems.

Gaussian Max-Value Entropy Search for Multi-Agent Bayesian Optimization

no code implementations10 Mar 2023 Haitong Ma, Tianpeng Zhang, Yixuan Wu, Flavio P. Calmon, Na Li

We focus on Entropy Search (ES), a sample-efficient BO algorithm that selects queries to maximize the mutual information about the maximum of the black-box function.

Bayesian Optimization

Semantic Video Moments Retrieval at Scale: A New Task and a Baseline

no code implementations15 Oct 2022 Na Li

In the 1st stage, our SVMR should take into account the fact that: 1) a positive candidate long video can contain plenty of irrelevant clips which are also semantically meaningful.

Retrieval Video Retrieval

Multi-armed Bandit Learning on a Graph

1 code implementation20 Sep 2022 Tianpeng Zhang, Kasper Johansson, Na Li

The graph defines the agent's freedom in selecting the next available nodes at each step.

Decision Making Decision Making Under Uncertainty

FedDAR: Federated Domain-Aware Representation Learning

no code implementations8 Sep 2022 Aoxiao Zhong, Hao He, Zhaolin Ren, Na Li, Quanzheng Li

To make sure the FL model is robust when facing heterogeneous data among FL clients, most efforts focus on personalizing models for clients.

Federated Learning Representation Learning

Dialogue Policies for Confusion Mitigation in Situated HRI

1 code implementation19 Aug 2022 Na Li, Robert Ross

Confusion is a mental state triggered by cognitive disequilibrium that can occur in many types of task-oriented interaction, including Human-Robot Interaction (HRI).

Cross-Age Speaker Verification: Learning Age-Invariant Speaker Embeddings

1 code implementation13 Jul 2022 Xiaoyi Qin, Na Li, Chao Weng, Dan Su, Ming Li

In this paper, we mine cross-age test sets based on the VoxCeleb dataset and propose our age-invariant speaker representation(AISR) learning method.

Age Estimation Speaker Verification

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

no code implementations6 Jun 2022 Runyu Zhang, Qinghua Liu, Huan Wang, Caiming Xiong, Na Li, Yu Bai

Next, we show that this framework instantiated with the Optimistic Follow-The-Regularized-Leader (OFTRL) algorithm at each state (and smooth value updates) can find an $\mathcal{\widetilde{O}}(T^{-5/6})$ approximate NE in $T$ iterations, and a similar algorithm with slightly modified value update rule achieves a faster $\mathcal{\widetilde{O}}(T^{-1})$ convergence rate.

Multi-agent Reinforcement Learning

Detecting Interlocutor Confusion in Situated Human-Avatar Dialogue: A Pilot Study

no code implementations6 Jun 2022 Na Li, John D. Kelleher, Robert Ross

To this end, in this paper, we present our initial research centred on a user-avatar dialogue scenario that we have developed to study the manifestation of confusion and in the long term its mitigation.

Transferring Studies Across Embodiments: A Case Study in Confusion Detection

no code implementations3 Jun 2022 Na Li, Robert Ross

Human-robot studies are expensive to conduct and difficult to control, and as such researchers sometimes turn to human-avatar interaction in the hope of faster and cheaper data collection that can be transferred to the robot domain.

A Survey on Distributed Online Optimization and Game

no code implementations1 May 2022 Xiuxian Li, Lihua Xie, Na Li

And the local cost function of each agent is often time-varying in dynamic and even adversarial environments.

Deep Learning-Based Intra Mode Derivation for Versatile Video Coding

no code implementations8 Apr 2022 Linwei Zhu, Yun Zhang, Na Li, Gangyi Jiang, Sam Kwong

To further improve the performance of intra coding in Versatile Video Coding (VVC), an intelligent intra mode derivation method is proposed in this paper, termed as Deep Learning based Intra Mode Derivation (DLIMD).

Multi-class Classification Quantization

The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge

no code implementations4 Feb 2022 Naijun Zheng, Na Li, Xixin Wu, Lingwei Meng, Jiawen Kang, Haibin Wu, Chao Weng, Dan Su, Helen Meng

This paper describes our speaker diarization system submitted to the Multi-channel Multi-party Meeting Transcription (M2MeT) challenge, where Mandarin meeting data were recorded in multi-channel format for diarization and automatic speech recognition (ASR) tasks.

Action Detection Activity Detection +6

Communication-Efficient Distributed SGD with Compressed Sensing

no code implementations15 Dec 2021 Yujie Tang, Vikram Ramanathan, Junshan Zhang, Na Li

We consider large scale distributed optimization over a set of edge devices connected to a central server, where the limited communication bandwidth between the server and edge devices imposes a significant bottleneck for the optimization procedure.

Distributed Optimization Federated Learning

Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees

no code implementations31 Oct 2021 YingYing Li, Subhro Das, Jeff Shamma, Na Li

We study the adaptive control of an unknown linear system with a quadratic cost function subject to safety constraints on both the states and actions.

Self-adaptive Multi-task Particle Swarm Optimization

no code implementations9 Oct 2021 Xiaolong Zheng, Deyun Zhou, Na Li, Yu Lei, Tao Wu, Maoguo Gong

In the focus search strategy, if there is no knowledge source benefit the optimization of a task, then all knowledge sources in the task's pool are forbidden to be utilized except the task, which helps to improve the performance of the proposed algorithm.

Evolutionary Algorithms Transfer Learning

A Benchmark for Gait Recognition under Occlusion Collected by Multi-Kinect SDAS

no code implementations19 Jul 2021 Na Li, Xinbo Zhao

We collect a new gait recognition database called OG RGB+D database, which breaks through the limitation of other gait databases and includes multimodal gait data of various occlusions (self-occlusion, active occlusion, and passive occlusion) by our multiple synchronous Azure Kinect DK sensors data acquisition system (multi-Kinect SDAS) that can be also applied in security situations.

3D Multi-Person Pose Estimation Gait Recognition +1

Applying VertexShuffle Toward 360-Degree Video Super-Resolution on Focused-Icosahedral-Mesh

no code implementations21 Jun 2021 Na Li, Yao Liu

We further apply our proposed methods on super resolution model, which is the first to propose a spherical super-resolution model that directly operates on a mesh representation of spherical pixels of 360-degree data.

Video Super-Resolution

Gradient play in stochastic games: stationary points, convergence, and sample complexity

no code implementations1 Jun 2021 Runyu Zhang, Zhaolin Ren, Na Li

We show that Nash equilibria (NEs) and first-order stationary policies are equivalent in this setting, and give a local convergence rate around strict NEs.

Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approach

no code implementations16 Feb 2021 Junshan Zhang, Na Li, Mehmet Dedeoglu

We consider a many-to-one wireless architecture for federated learning at the network edge, where multiple edge devices collaboratively train a model using local data.

Federated Learning

Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Control

2 code implementations8 Feb 2021 Yang Zheng, Yujie Tang, Na Li

This paper revisits the classical Linear Quadratic Gaussian (LQG) control from a modern optimization perspective.

Policy Gradient Methods Optimization and Control Systems and Control Systems and Control Dynamical Systems

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

no code implementations27 Jan 2021 Xin Chen, Guannan Qu, Yujie Tang, Steven Low, Na Li

With large-scale integration of renewable generation and distributed energy resources, modern power systems are confronted with new operational challenges, such as growing complexity, increasing uncertainty, and aggravating volatility.

Decision Making energy management +2

Meta-Learning with Implicit Processes

no code implementations1 Jan 2021 Yizhou Chen, Dong Li, Na Li, TONG LIANG, Shizhuo Zhang, Bryan Kian Hsiang Low

This paper presents a novel implicit process-based meta-learning (IPML) algorithm that, in contrast to existing works, explicitly represents each task as a continuous latent vector and models its probabilistic belief within the highly expressive IP framework.


Modelling General Properties of Nouns by Selectively Averaging Contextualised Embeddings

no code implementations4 Dec 2020 Na Li, Zied Bouraoui, Jose Camacho Collados, Luis Espinosa-Anke, Qing Gu, Steven Schockaert

While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, such vectors continue to play an important role in tasks where words need to be modelled in the absence of linguistic context.

Knowledge Base Completion

On Disambiguating Authors: Collaboration Network Reconstruction in a Bottom-up Manner

1 code implementation29 Nov 2020 Na Li, Renyu Zhu, Xiaoxu Zhou, Xiangnan He, Wenyuan Cai, Ming Gao, Aoying Zhou

In this paper, we model the author disambiguation as a collaboration network reconstruction problem, and propose an incremental and unsupervised author disambiguation method, namely IUAD, which performs in a bottom-up manner.

Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms

no code implementations NeurIPS 2020 YingYing Li, Na Li

To address this question, we introduce a gradient-based online algorithm, Receding Horizon Inexact Gradient (RHIG), and analyze its performance by dynamic regrets in terms of the temporal variation of the environment and the prediction errors.

LQR with Tracking: A Zeroth-order Approach and Its Global Convergence

no code implementations3 Nov 2020 Zhaolin Ren, Aoxiao Zhong, Na Li

In this work, we consider the general case where the target is allowed to be arbitrary, which we refer to as the LQR tracking problem.

Multi-agent Reinforcement Learning

Replay and Synthetic Speech Detection with Res2net Architecture

2 code implementations28 Oct 2020 Xu Li, Na Li, Chao Weng, Xunying Liu, Dan Su, Dong Yu, Helen Meng

This multiple scaling mechanism significantly improves the countermeasure's generalizability to unseen spoofing attacks.

Feature Engineering Synthetic Speech Detection

ASCII: ASsisted Classification with Ignorance Interchange

no code implementations21 Oct 2020 Jiaying Zhou, Xun Xian, Na Li, Jie Ding

In this paper, we propose a method named ASCII for an agent to improve its classification performance through assistance from other agents.

Classification General Classification

Online Learning and Distributed Control for Residential Demand Response

no code implementations11 Oct 2020 Xin Chen, YingYing Li, Jun Shimada, Na Li

This paper studies the automated control method for regulating air conditioner (AC) loads in incentive-based residential demand response (DR).

Stochastic Optimization Thompson Sampling

Online Optimal Control with Affine Constraints

no code implementations10 Oct 2020 YingYing Li, Subhro Das, Na Li

We show that OGD-BZ can achieve a policy regret upper bound that is the square root of the horizon length multiplied by some logarithmic terms of the horizon length under proper algorithm parameters.

Emergence of Chern insulating states in non-Magic angle twisted bilayer graphene

no code implementations8 Oct 2020 Cheng Shen, Jianghua Ying, Le Liu, Jianpeng Liu, Na Li, Shuopei Wang, Jian Tang, Yanchong Zhao, Yanbang Chu, Kenji Watanabe, Takashi Taniguchi, Rong Yang, Dongxia Shi, Fanming Qu, Li Lu, Wei Yang, Guangyu Zhang

For {\theta}=1. 25{\deg}, we observe an emergence of topological insulating states at hole side with a sequence of Chern number |C|=4-|v|, where v is the number of electrons (holes) in moir\'e unite cell.

Mesoscale and Nanoscale Physics Materials Science

Stem-leaf segmentation and phenotypic trait extraction of maize shoots from three-dimensional point cloud

1 code implementation7 Sep 2020 Chao Zhu, Teng Miao, Tongyu Xu, Tao Yang, Na Li

However, automatic stem-leaf segmentation of maize shoots from three-dimensional (3D) point clouds remains challenging, especially for new emerging leaves that are very close and wrapped together during the seedling stage.

Non-asymptotic Identification of Linear Dynamical Systems Using Multiple Trajectories

1 code implementation1 Sep 2020 Yang Zheng, Na Li

For unstable systems, our results suggest that the Markov parameters are harder to estimate in the presence of process noise.

Optimization and Control Systems and Control Systems and Control Dynamical Systems

Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification

no code implementations11 Jun 2020 Xu Li, Na Li, Jinghua Zhong, Xixin Wu, Xunying Liu, Dan Su, Dong Yu, Helen Meng

Orthogonal to prior approaches, this work proposes to defend ASV systems against adversarial attacks with a separate detection network, rather than augmenting adversarial data into ASV training.

Binary Classification Data Augmentation +1

Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward

no code implementations NeurIPS 2020 Guannan Qu, Yiheng Lin, Adam Wierman, Na Li

It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exponentially large in the number of agents.

Multi-agent Reinforcement Learning reinforcement-learning +1

Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems

no code implementations L4DC 2020 Guannan Qu, Adam Wierman, Na Li

We study reinforcement learning (RL) in a setting with a network of agents whose states and actions interact in a local manner where the objective is to find localized policies such that the (discounted) global reward is maximized.

reinforcement-learning Reinforcement Learning (RL)

Leveraging Two-Stage Adaptive Robust Optimization for Power Flexibility Aggregation

no code implementations7 May 2020 Xin Chen, Na Li

This method is applicable to aggregate only the active (or reactive) power, and the joint active-reactive power domain.

Vocal Bursts Valence Prediction

A Reliability-aware Multi-armed Bandit Approach to Learn and Select Users in Demand Response

no code implementations20 Mar 2020 YingYing Li, Qinran Hu, Na Li

One challenge in the optimization and control of societal systems is to handle the unknown and uncertain user behavior.

Avg Thompson Sampling

Online Residential Demand Response via Contextual Multi-Armed Bandits

no code implementations7 Mar 2020 Xin Chen, Yutong Nie, Na Li

Residential loads have great potential to enhance the efficiency and reliability of electricity systems via demand response (DR) programs.

Decision Making Multi-Armed Bandits +1

Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach

1 code implementation L4DC 2020 Ying-Ying Li, Yujie Tang, Runyu Zhang, Na Li

We propose a Zero-Order Distributed Policy Optimization algorithm (ZODPO) that learns linear local controllers in a distributed fashion, leveraging the ideas of policy gradient, zero-order optimization and consensus algorithms.

Reinforcement Learning (RL)

Scalable Reinforcement Learning for Multi-Agent Networked Systems

no code implementations5 Dec 2019 Guannan Qu, Adam Wierman, Na Li

We study reinforcement learning (RL) in a setting with a network of agents whose states and actions interact in a local manner where the objective is to find localized policies such that the (discounted) global reward is maximized.

reinforcement-learning Reinforcement Learning (RL)

Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure

no code implementations15 Sep 2019 Guannan Qu, Na Li

Further, under some special conditions, we prove that the gap between the approximated reward function and the true reward function is decaying exponentially fast as the length of the truncated Markov process gets longer.

DV3+HED+: A DCNNs-based Framework to Monitor Temporary Works and ESAs in Railway Construction Project Using VHR Satellite Images

1 code implementation29 Aug 2019 Rui Guo, Ronghua Liu, Na Li, Wei Liu

Current VHR(Very High Resolution) satellite images enable the detailed monitoring of the earth and can capture the ongoing works of railway construction.

Edge Detection Semantic Segmentation

Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis

1 code implementation NeurIPS 2019 Ying-Ying Li, Xin Chen, Na Li

In addition, we provide a fundamental limit of the dynamic regret for any online algorithms by considering linear quadratic tracking problems.

Optimization and Control

Learning discriminative features in sequence training without requiring framewise labelled data

no code implementations16 May 2019 Jun Wang, Dan Su, Jie Chen, Shulin Feng, Dongpeng Ma, Na Li, Dong Yu

We propose a novel method which simultaneously models both the sequence discriminative training and the feature discriminative learning within a single network architecture, so that it can learn discriminative deep features in sequence training that obviates the need for presegmented training data.

On Maintaining Linear Convergence of Distributed Learning and Optimization under Limited Communication

no code implementations26 Feb 2019 Sindri Magnússon, Hossein Shokri-Ghadikolaei, Na Li

The communication time of these algorithms follows a complex interplay between a) the algorithm's convergence properties, b) the compression scheme, and c) the transmission rate offered by the digital channel.

BIG-bench Machine Learning Distributed Optimization

An automatic water detection approach based on Dempster-Shafer theory for multi spectral images

no code implementations9 Aug 2017 Na Li, Arnaud Martin, Rémi Estival

Detection of surface water in natural environment via multi-spectral imagery has been widely utilized in many fields, such land cover identification.

Land Cover Classification

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