Search Results for author:
Found 90 papers, 18 papers with code
Primal-Dual Spectral Representation for Off-policy Evaluation
We highlight that our algorithm, SpectralDICE, is the first to leverage the linear representation of primal-dual variables that is both computation and sample efficient, the performance of which is supported by a rigorous theoretical sample complexity guarantee and a thorough empirical evaluation on various benchmarks.
Risk-sensitive Affine Control Synthesis for Stationary LTI Systems
To address deviations from expected performance in stochastic systems, we propose a risk-sensitive control synthesis method to minimize certain risk measures over the limiting stationary distribution.
Scalable spectral representations for multi-agent reinforcement learning in network MDPs
Network Markov Decision Processes (MDPs), a popular model for multi-agent control, pose a significant challenge to efficient learning due to the exponential growth of the global state-action space with the number of agents.
Distributed Thompson sampling under constrained communication
We apply distributed Thompson sampling, using a Gaussian process as a surrogate model, to approach the multi-agent Bayesian optimization problem.
Drift to Remember
Tested on GPT-2 and RoBERTa, DriftNet is a robust, cost-effective solution for lifelong learning in LLMs.
Model-in-the-Loop (MILO): Accelerating Multimodal AI Data Annotation with LLMs
The growing demand for AI training data has transformed data annotation into a global industry, but traditional approaches relying on human annotators are often time-consuming, labor-intensive, and prone to inconsistent quality.
Enhancing Preference-based Linear Bandits via Human Response Time
Theoretical and empirical analyses show that for queries with strong preferences, response times complement choices by providing extra information about preference strength, leading to significantly improved utility estimation.
Towards Evaluating and Building Versatile Large Language Models for Medicine
To promote further advancements in the application of LLMs to clinical challenges, we have made the MedS-Ins dataset fully accessible and invite the research community to contribute to its expansion. Additionally, we have launched a dynamic leaderboard for MedS-Bench, which we plan to regularly update the test set to track progress and enhance the adaptation of general LLMs to the medical domain.
LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance
We pretrain a variational autoencoder structure using the noted open-source So-VITS-SVC project based on the VITS framework, which is then used for the LDM training.
Support-Query Prototype Fusion Network for Few-shot Medical Image Segmentation
Currently, most studies employ a prototype-based approach, in which prototypical networks are used to construct prototypes from the support set, guiding the processing of the query set to obtain the final results.
Multi-Task Learning for Fatigue Detection and Face Recognition of Drivers via Tree-Style Space-Channel Attention Fusion Network
These systems typically need to handle multiple tasks simultaneously, such as detecting fatigue driving and recognizing the driver's identity.
Autonomous Robotic Ultrasound System for Liver Follow-up Diagnosis: Pilot Phantom Study
The paper introduces a novel autonomous robot ultrasound (US) system targeting liver follow-up scans for outpatients in local communities.
Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds
We show that this inevitable linear factor of $n$ is due to the learning error of the observer's column space in the presence of high-dimensional noises.
Efficient Duple Perturbation Robustness in Low-rank MDPs
The pursuit of robustness has recently been a popular topic in reinforcement learning (RL) research, yet the existing methods generally suffer from efficiency issues that obstruct their real-world implementation.
Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpoint
Moreover, to handle the sim-to-real gap in the dynamics, we propose a skill discovery algorithm that learns new skills caused by the sim-to-real gap from real-world data.
Modelling Commonsense Commonalities with Multi-Facet Concept Embeddings
We show that this leads to embeddings which capture a more diverse range of commonsense properties, and consistently improves results in downstream tasks such as ultra-fine entity typing and ontology completion.
Ontology Completion with Natural Language Inference and Concept Embeddings: An Analysis
One line of work treats this task as a Natural Language Inference (NLI) problem, thus relying on the knowledge captured by language models to identify the missing knowledge.
Aggregate Peak EV Charging Demand: The Impact of Segmented Network Tariffs
In this paper, we compare the effect of a multi-level segmented network tariff with and without dynamic energy prices for individual EV users on the aggregate peak demand.
Exploring the Capabilities and Limitations of Large Language Models in the Electric Energy Sector
Large Language Models (LLMs) as chatbots have drawn remarkable attention thanks to their versatile capability in natural language processing as well as in a wide range of tasks.
An AI-Driven Approach to Wind Turbine Bearing Fault Diagnosis from Acoustic Signals
This study aimed to develop a deep learning model for the classification of bearing faults in wind turbine generators from acoustic signals.
Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
Data users have been endowed with the right to be forgotten of their data.
TS-RSR: A provably efficient approach for batch bayesian optimization
This paper presents a new approach for batch Bayesian Optimization (BO) called Thompson Sampling-Regret to Sigma Ratio directed sampling (TS-RSR), where we sample a new batch of actions by minimizing a Thompson Sampling approximation of a regret to uncertainty ratio.
Can We Improve Channel Reciprocity via Loop-back Compensation for RIS-assisted Physical Layer Key Generation
The results demonstrate a significant improvement in both the rate of key generation assisted by the RIS and the consistency of the generated keys, showing great potential for the practical deployment of our LoCKey in future wireless systems.
Scalable Reinforcement Learning for Linear-Quadratic Control of Networks
In this work, we study a special class of such problems where distributed state feedback controllers can give near-optimal performance.
Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis
The reward of the system is modeled as a weighted sum of the rewards the agents observe, where the weights capture some transformation of the reward associated with multiple agents sampling the same node at the same time.
Ocean Data Quality Assessment through Outlier Detection-enhanced Active Learning
Ocean and climate research benefits from global ocean observation initiatives such as Argo, GLOSS, and EMSO.
InstructPipe: Building Visual Programming Pipelines with Human Instructions Using LLMs
Visual programming has the potential of providing novice programmers with a low-code experience to build customized processing pipelines.
MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control
In this paper, we introduce a new class of parameterized controllers, drawing inspiration from Model Predictive Control (MPC).
What do Deck Chairs and Sun Hats Have in Common? Uncovering Shared Properties in Large Concept Vocabularies
We show that by augmenting the label set with shared properties, we can improve the performance of the state-of-the-art models for this task.
Towards Carbon-Free Electricity: A Flow-Based Framework for Power Grid Carbon Accounting and Decarbonization
This paper introduces a comprehensive framework aimed at advancing research and policy development in the realm of decarbonization within electric power systems.
Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
This paper introduces a new formulation for risk-sensitive MDPs, which assesses risk in a slightly different manner compared to the classical Markov risk measure (Ruszczy\'nski 2010), and establishes its equivalence with a class of soft robust MDP (RMDP) problems, including the standard RMDP as a special case.
Non-asymptotic System Identification for Linear Systems with Nonlinear Policies
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
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.
Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Models
Second, concept embeddings should capture the semantic properties of concepts, whereas contextualised word vectors are also affected by other factors.
Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding
This paper presents an approach, Spectral Dynamics Embedding Control (SDEC), to optimal control for nonlinear stochastic systems.
Decentralized Riemannian natural gradient methods with Kronecker-product approximations
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
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.
Latent Variable Representation for Reinforcement Learning
Theoretically, we establish the sample complexity of the proposed approach in the online and offline settings.
Model-based Reinforcement Learning
reinforcement-learning
+2
Learning to Optimize with Stochastic Dominance Constraints
In real-world decision-making, uncertainty is important yet difficult to handle.
Semantic Video Moments Retrieval at Scale: A New Task and a Baseline
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.
Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies
Gradient-based methods have been widely used for system design and optimization in diverse application domains.
Multi-armed Bandit Learning on a Graph
The graph defines the agent's freedom in selecting the next available nodes at each step.
FedDAR: Federated Domain-Aware Representation Learning
To make sure the FL model is robust when facing heterogeneous data among FL clients, most efforts focus on personalizing models for clients.
Dialogue Policies for Confusion Mitigation in Situated HRI
Confusion is a mental state triggered by cognitive disequilibrium that can occur in many types of task-oriented interaction, including Human-Robot Interaction (HRI).
A Hybrid Deep Feature-Based Deformable Image Registration Method for Pathology Images
Deformable image registration is a necessary technique for fusing multi-modal pathology slices.
Cross-Age Speaker Verification: Learning Age-Invariant Speaker Embeddings
In this paper, we mine cross-age test sets based on the VoxCeleb dataset and propose our age-invariant speaker representation(AISR) learning method.
Detecting Interlocutor Confusion in Situated Human-Avatar Dialogue: A Pilot Study
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.
Policy Optimization for Markov Games: Unified Framework and Faster Convergence
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.
Transferring Studies Across Embodiments: A Case Study in Confusion Detection
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
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
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).
The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge
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.
Communication-Efficient Distributed SGD with Compressed Sensing
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.
Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees
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
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.
A Benchmark for Gait Recognition under Occlusion Collected by Multi-Kinect SDAS
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.
Applying VertexShuffle Toward 360-Degree Video Super-Resolution on Focused-Icosahedral-Mesh
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.
Gradient play in stochastic games: stationary points, convergence, and sample complexity
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
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.
Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Control
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
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.
Demand Forecasting for Platelet Usage: from Univariate Time Series to Multivariate Models
Platelet products are both expensive and have very short shelf lives.
Meta-Learning with Implicit Processes
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
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.
On Disambiguating Authors: Collaboration Network Reconstruction in a Bottom-up Manner
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
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
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.
Replay and Synthetic Speech Detection with Res2net Architecture
This multiple scaling mechanism significantly improves the countermeasure's generalizability to unseen spoofing attacks.
ASCII: ASsisted Classification with Ignorance Interchange
In this paper, we propose a method named ASCII for an agent to improve its classification performance through assistance from other agents.
Online Learning and Distributed Control for Residential Demand Response
This paper studies the automated control method for regulating air conditioner (AC) loads in incentive-based residential demand response (DR).
Online Optimal Control with Affine Constraints
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
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
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
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
Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward
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
Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification
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.
Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems
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.
Leveraging Two-Stage Adaptive Robust Optimization for Power Flexibility Aggregation
This method is applicable to aggregate only the active (or reactive) power, and the joint active-reactive power domain.
JointsGait:A model-based Gait Recognition Method based on Gait Graph Convolutional Networks and Joints Relationship Pyramid Mapping
However, appearance features suffer from external factors which can cause drastic appearance variations, e. g. clothing.
A Reliability-aware Multi-armed Bandit Approach to Learn and Select Users in Demand Response
One challenge in the optimization and control of societal systems is to handle the unknown and uncertain user behavior.
Online Residential Demand Response via Contextual Multi-Armed Bandits
Residential loads have great potential to enhance the efficiency and reliability of electricity systems via demand response (DR) programs.
MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis
The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications.
Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach
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.
Scalable Reinforcement Learning for Multi-Agent Networked Systems
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.
Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure
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
Current VHR(Very High Resolution) satellite images enable the detailed monitoring of the earth and can capture the ongoing works of railway construction.
Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis
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
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
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.
An automatic water detection approach based on Dempster-Shafer theory for multi spectral images
Detection of surface water in natural environment via multi-spectral imagery has been widely utilized in many fields, such land cover identification.
