Search Results for author: Shuai Li

Found 84 papers, 18 papers with code

LST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform

no code implementations ECCV 2020 Lida Li, Kun Wang, Shuai Li, Xiangchu Feng, Lei Zhang

The 2D convolutional (Conv2d) layer is the fundamental element to a deep convolutional neural network (CNN).

Thompson Sampling for Bandit Learning in Matching Markets

1 code implementation26 Apr 2022 Fang Kong, Junming Yin, Shuai Li

The problem of two-sided matching markets has a wide range of real-world applications and has been extensively studied in the literature.

Multi-Armed Bandits

Learning of Global Objective for Network Flow in Multi-Object Tracking

no code implementations30 Mar 2022 Shuai Li, Yu Kong, Hamid Rezatofighi

This paper concerns the problem of multi-object tracking based on the min-cost flow (MCF) formulation, which is conventionally studied as an instance of linear program.

Multi-Object Tracking

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds

1 code implementation19 Mar 2022 Chenhang He, Ruihuang Li, Shuai Li, Lei Zhang

VoxSeT is built upon a voxel-based set attention (VSA) module, which reduces the self-attention in each voxel by two cross-attentions and models features in a hidden space induced by a group of latent codes.

3D Object Detection

Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation

1 code implementation18 Mar 2022 Ruihuang Li, Shuai Li, Chenhang He, Yabin Zhang, Xu Jia, Lei Zhang

One popular solution to this challenging task is self-training, which selects high-scoring predictions on target samples as pseudo labels for training.

Semantic Segmentation

Towards Robust 2D Convolution for Reliable Visual Recognition

no code implementations18 Mar 2022 Lida Li, Shuai Li, Kun Wang, Xiangchu Feng, Lei Zhang

2D convolution (Conv2d), which is responsible for extracting features from the input image, is one of the key modules of a convolutional neural network (CNN).

A Dual Weighting Label Assignment Scheme for Object Detection

1 code implementation18 Mar 2022 Shuai Li, Chenhang He, Ruihuang Li, Lei Zhang

Existing LA methods mostly focus on the design of pos weighting function, while the neg weight is directly derived from the pos weight.

Object Detection POS

A density peaks clustering algorithm with sparse search and K-d tree

no code implementations2 Mar 2022 Yunxiao Shan, Shu Li, Fuxiang Li, Yuxin Cui, Shuai Li, Minghua Chen, Xunjun He

Secondly, a sparse search strategy is proposed to accelerate the computation of relative-separation with the intersection between the set of k nearest neighbors and the set consisting of the data points with larger local density for any data point.

Pursuit-evasion differential games of players with different speeds in spaces of different dimensions

no code implementations28 Feb 2022 Shuai Li, Chen Wang, Guangming Xie

We study pursuit-evasion differential games between a faster pursuer moving in 3D space and an evader moving in a plane.

Knowledge-inspired 3D Scene Graph Prediction in Point Cloud

no code implementations NeurIPS 2021 Shoulong Zhang, Shuai Li, Aimin Hao, Hong Qin

Unlike conventional methods that learn knowledge embedding and regular patterns from encoded visual information, we propose to suppress the misunderstandings caused by appearance similarities and other perceptual confusion.

The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle

no code implementations NeurIPS 2021 Fang Kong, Yueran Yang, Wei Chen, Shuai Li

These are the first theoretical results for TS to solve CMAB with a common approximation oracle and break the misconception that TS cannot work with approximation oracles.

Combinatorial Optimization

Incentivizing an Unknown Crowd

no code implementations9 Sep 2021 Jing Dong, Shuai Li, Baoxiang Wang

Motivated by the common strategic activities in crowdsourcing labeling, we study the problem of sequential eliciting information without verification (EIWV) for workers with a heterogeneous and unknown crowd.

reinforcement-learning

Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography

no code implementations12 Aug 2021 Joshua D. Rego, Huaijin Chen, Shuai Li, Jinwei Gu, Suren Jayasuriya

The lensless pinhole camera is perhaps the earliest and simplest form of an imaging system using only a pinhole-sized aperture in place of a lens.

Image Restoration

A Global Appearance and Local Coding Distortion based Fusion Framework for CNN based Filtering in Video Coding

no code implementations24 Jun 2021 Jian Yue, Yanbo Gao, Shuai Li, Hui Yuan, Frédéric Dufaux

To the best of our knowledge, we are the first one that clearly characterizes the video filtering process from the above global appearance and local coding distortion restoration aspects with experimental verification, providing a clear pathway to developing filter techniques.

Frame

Cooperative Stochastic Multi-agent Multi-armed Bandits Robust to Adversarial Corruptions

no code implementations8 Jun 2021 Junyan Liu, Shuai Li, Dapeng Li

Our algorithm not only achieves near-optimal regret in the stochastic setting, but also obtains a regret with an additive term of corruption in the corrupted setting, while maintaining efficient communication.

Multi-Armed Bandits

On Learning to Rank Long Sequences with Contextual Bandits

no code implementations7 Jun 2021 Anirban Santara, Claudio Gentile, Gaurav Aggarwal, Shuai Li

Motivated by problems of learning to rank long item sequences, we introduce a variant of the cascading bandit model that considers flexible length sequences with varying rewards and losses.

Learning-To-Rank Multi-Armed Bandits

Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners

no code implementations1 Jun 2021 Yabin Zhang, Haojian Zhang, Bin Deng, Shuai Li, Kui Jia, Lei Zhang

Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques.

Unsupervised Domain Adaptation

Understanding Bandits with Graph Feedback

no code implementations NeurIPS 2021 Houshuang Chen, Zengfeng Huang, Shuai Li, Chihao Zhang

We propose the notions of the fractional weak domination number $\delta^*$ and the $k$-packing independence number capturing upper bound and lower bound for the regret respectively.

Cascading Bandit under Differential Privacy

no code implementations24 May 2021 Kun Wang, Jing Dong, Baoxiang Wang, Shuai Li, Shuo Shao

This paper studies \emph{differential privacy (DP)} and \emph{local differential privacy (LDP)} in cascading bandits.

Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network

1 code implementation CVPR 2021 Ruicheng Feng, Chongyi Li, Huaijin Chen, Shuai Li, Chen Change Loy, Jinwei Gu

Recent development of Under-Display Camera (UDC) systems provides a true bezel-less and notch-free viewing experience on smartphones (and TV, laptops, tablets), while allowing images to be captured from the selfie camera embedded underneath.

Image Restoration

Conservative Contextual Combinatorial Cascading Bandit

no code implementations17 Apr 2021 Kun Wang, Canzhe Zhao, Shuai Li, Shuo Shao

We propose the novel \emph{conservative contextual combinatorial cascading bandit ($C^4$-bandit)}, a cascading online learning game which incorporates the conservative mechanism.

Decision Making online learning +1

An Adversarial Imitation Click Model for Information Retrieval

1 code implementation13 Apr 2021 Xinyi Dai, Jianghao Lin, Weinan Zhang, Shuai Li, Weiwen Liu, Ruiming Tang, Xiuqiang He, Jianye Hao, Jun Wang, Yong Yu

Modern information retrieval systems, including web search, ads placement, and recommender systems, typically rely on learning from user feedback.

Imitation Learning Information Retrieval +1

Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation

1 code implementation CVPR 2021 Minghan Li, Shuai Li, Lida Li, Lei Zhang

To further explore temporal correlation among video frames, we aggregate a temporal fusion module to infer instance masks from each frame to its adjacent frames, which helps our framework to handle challenging videos such as motion blur, partial occlusion and unusual object-to-camera poses.

Frame Instance Segmentation +2

Decentralized Circle Formation Control for Fish-like Robots in the Real-world via Reinforcement Learning

no code implementations9 Mar 2021 Tianhao Zhang, Yueheng Li, Shuai Li, Qiwei Ye, Chen Wang, Guangming Xie

In this paper, the circle formation control problem is addressed for a group of cooperative underactuated fish-like robots involving unknown nonlinear dynamics and disturbances.

reinforcement-learning

Combinatorial Bandits under Strategic Manipulations

1 code implementation25 Feb 2021 Jing Dong, Ke Li, Shuai Li, Baoxiang Wang

Strategic behavior against sequential learning methods, such as "click framing" in real recommendation systems, have been widely observed.

Multi-Armed Bandits Recommendation Systems

A Two-stream Neural Network for Pose-based Hand Gesture Recognition

no code implementations22 Jan 2021 Chuankun Li, Shuai Li, Yanbo Gao, Xiang Zhang, Wanqing Li

The self-attention based graph convolutional network has a dynamic self-attention mechanism to adaptively exploit the relationships of all hand joints in addition to the fixed topology and local feature extraction in the GCN.

Action Recognition Hand Gesture Recognition +1

A robust and generalizable immune-relatedsignature for sepsis diagnostics

no code implementations23 Nov 2020 Yueran Yang, Yu Zhang, Shuai Li, Xubin Zheng, Man-Hon Wong, Kwong-Sak Leung, Lixin Cheng

High-throughput sequencing can detect tens of thousands of genes in parallel, providing opportunities for improving the diagnostic accuracy of multiple diseases including sepsis, which is an aggressive inflammatory response to infection that can cause organ failure and death.

Towards Understanding the Regularization of Adversarial Robustness on Neural Networks

no code implementations ICML 2020 Yuxin Wen, Shuai Li, Kui Jia

However, it is observed that such methods would lead to standard performance degradation, i. e., the degradation on natural examples.

Adversarial Robustness

Online Influence Maximization under Linear Threshold Model

no code implementations NeurIPS 2020 Shuai Li, Fang Kong, Kejie Tang, Qizhi Li, Wei Chen

Based on the linear structure in node activations, we incorporate ideas from linear bandits and design an algorithm LT-LinUCB that is consistent with the observed feedback.

online learning

A Framework of Combining Short-Term Spatial/Frequency Feature Extraction and Long-Term IndRNN for Activity Recognition

no code implementations1 Nov 2020 Beidi Zhao, Shuai Li, Yanbo Gao, Chuankun Li, Wanqing Li

Smartphone sensors based human activity recognition is attracting increasing interests nowadays with the popularization of smartphones.

Activity Recognition

EqSpike: Spike-driven Equilibrium Propagation for Neuromorphic Implementations

no code implementations15 Oct 2020 Erwann Martin, Maxence Ernoult, Jérémie Laydevant, Shuai Li, Damien Querlioz, Teodora Petrisor, Julie Grollier

Finding spike-based learning algorithms that can be implemented within the local constraints of neuromorphic systems, while achieving high accuracy, remains a formidable challenge.

Deforming the Loss Surface to Affect the Behaviour of the Optimizer

no code implementations14 Sep 2020 Liangming Chen, Long Jin, Xiujuan Du, Shuai Li, Mei Liu

With visualizations of loss landscapes, we evaluate the flatnesses of minima obtained by both the original optimizer and optimizers enhanced by VDMs on CIFAR-100.

Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter

no code implementations10 Aug 2020 Zhen-Yu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin

In sharp contrast to the state-of-the-art (SOTA) methods that focus on learning pixel-wise saliency in "single image" using perceptual clues mainly, our method has investigated the "object-level semantic ranks between multiple images", of which the methodology is more consistent with the real human attention mechanism.

Re-Ranking RGB Salient Object Detection +1

A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset

no code implementations7 Aug 2020 Zhen-Yu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin

Compared with the conventional hand-crafted approaches, the deep learning based methods have achieved tremendous performance improvements by training exquisitely crafted fancy networks over large-scale training sets.

RGB Salient Object Detection Salient Object Detection

Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection

1 code implementation7 Aug 2020 Xuehao Wang, Shuai Li, Chenglizhao Chen, Yuming Fang, Aimin Hao, Hong Qin

Existing RGB-D salient object detection methods treat depth information as an independent component to complement its RGB part, and widely follow the bi-stream parallel network architecture.

RGB-D Salient Object Detection Salient Object Detection

Knowing Depth Quality In Advance: A Depth Quality Assessment Method For RGB-D Salient Object Detection

1 code implementation7 Aug 2020 Xuehao Wang, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin

Previous RGB-D salient object detection (SOD) methods have widely adopted deep learning tools to automatically strike a trade-off between RGB and D (depth), whose key rationale is to take full advantage of their complementary nature, aiming for a much-improved SOD performance than that of using either of them solely.

RGB-D Salient Object Detection RGB Salient Object Detection +1

A Plug-and-play Scheme to Adapt Image Saliency Deep Model for Video Data

1 code implementation2 Aug 2020 Yunxiao Li, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin

With the rapid development of deep learning techniques, image saliency deep models trained solely by spatial information have occasionally achieved detection performance for video data comparable to that of the models trained by both spatial and temporal information.

Video Saliency Detection

Deforming the Loss Surface

no code implementations24 Jul 2020 Liangming Chen, Long Jin, Xiujuan Du, Shuai Li, Mei Liu

Furthermore, the flatter minima could be obtained by exploiting the proposed deformation functions, which is verified on CIFAR-100, with visualizations of loss landscapes near the critical points obtained by both the original optimizer and optimizer enhanced by deformation functions.

Fast Distributed Bandits for Online Recommendation Systems

no code implementations16 Jul 2020 Kanak Mahadik, Qingyun Wu, Shuai Li, Amit Sabne

This algorithm lazily creates clusters in a distributed manner, and dramatically reduces the network data sharing requirement, achieving high scalability.

Recommendation Systems

Learning Various Length Dependence by Dual Recurrent Neural Networks

no code implementations28 May 2020 Chenpeng Zhang, Shuai Li, Mao Ye, Ce Zhu, Xue Li

Many variants of RNN have been proposed to solve the gradient problems of training RNNs and process long sequences.

A Novel and Efficient Tumor Detection Framework for Pancreatic Cancer via CT Images

no code implementations11 Feb 2020 Zhengdong Zhang, Shuai Li, Ziyang Wang, Yun Lu

Experimental results achieve competitive performance in detection with the AUC of 0. 9455, which outperforms other state-of-the-art methods to our best of knowledge, demonstrating the proposed framework can detect the tumor of pancreatic cancer efficiently and accurately.

Computed Tomography (CT)

Fractional order graph neural network

no code implementations5 Jan 2020 Zijian Liu, Chunbo Luo, Shuai Li, Peng Ren, Geyong Min

This paper proposes fractional order graph neural networks (FGNNs), optimized by the approximation strategy to address the challenges of local optimum of classic and fractional graph neural networks which are specialised at aggregating information from the feature and adjacent matrices of connected nodes and their neighbours to solve learning tasks on non-Euclidean data such as graphs.

Object Recognition

The Gambler's Problem and Beyond

no code implementations ICLR 2020 Baoxiang Wang, Shuai Li, Jiajin Li, Siu On Chan

We analyze the Gambler's problem, a simple reinforcement learning problem where the gambler has the chance to double or lose the bets until the target is reached.

Q-Learning reinforcement-learning

Contextual Combinatorial Conservative Bandits

no code implementations26 Nov 2019 Xiaojin Zhang, Shuai Li, Weiwen Liu, Shengyu Zhang

The problem of multi-armed bandits (MAB) asks to make sequential decisions while balancing between exploitation and exploration, and have been successfully applied to a wide range of practical scenarios.

Multi-Armed Bandits

Deep Independently Recurrent Neural Network (IndRNN)

1 code implementation11 Oct 2019 Shuai Li, Wanqing Li, Chris Cook, Yanbo Gao

Recurrent neural networks (RNNs) are known to be difficult to train due to the gradient vanishing and exploding problems and thus difficult to learn long-term patterns and construct deep networks.

Language Modelling Sequential Image Classification +1

Dynamic Anchor Feature Selection for Single-Shot Object Detection

no code implementations ICCV 2019 Shuai Li, Lingxiao Yang, Jianqiang Huang, Xian-Sheng Hua, Lei Zhang

In this paper, we present a dynamic feature selection operation to select new pixels in a feature map for each refined anchor received from the ARM.

Object Detection

Learning to Synthesize: Robust Phase Retrieval at Low Photon counts

no code implementations26 Jul 2019 Mo Deng, Shuai Li, Alexandre Goy, Iksung Kang, George Barbastathis

The quality of inverse problem solutions obtained through deep learning [Barbastathis et al, 2019] is limited by the nature of the priors learned from examples presented during the training phase.

Orthogonal Deep Neural Networks

1 code implementation15 May 2019 Kui Jia, Shuai Li, Yuxin Wen, Tongliang Liu, DaCheng Tao

To this end, we first prove that DNNs are of local isometry on data distributions of practical interest; by using a new covering of the sample space and introducing the local isometry property of DNNs into generalization analysis, we establish a new generalization error bound that is both scale- and range-sensitive to singular value spectrum of each of networks' weight matrices.

Image Classification

Convergence analysis of beetle antennae search algorithm and its applications

1 code implementation4 Apr 2019 Yinyan Zhang, Shuai Li, Bin Xu

The beetle antennae search algorithm was recently proposed and investigated for solving global optimization problems.

Stochastic Online Learning with Probabilistic Graph Feedback

no code implementations4 Mar 2019 Shuai Li, Wei Chen, Zheng Wen, Kwong-Sak Leung

We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability $p_{ij}$.

online learning

Improved Algorithm on Online Clustering of Bandits

no code implementations25 Feb 2019 Wei Chen, Shuai Li, Kwong-Sak Leung

We generalize the setting of online clustering of bandits by allowing non-uniform distribution over user frequencies.

Online Clustering

Measure, Manifold, Learning, and Optimization: A Theory Of Neural Networks

no code implementations30 Nov 2018 Shuai Li

We present a formal measure-theoretical theory of neural networks (NN) built on probability coupling theory.

Learning to synthesize: splitting and recombining low and high spatial frequencies for image recovery

no code implementations19 Nov 2018 Mo Deng, Shuai Li, George Barbastathis

Deep Neural Network (DNN)-based image reconstruction, despite many successes, often exhibits uneven fidelity between high and low spatial frequency bands.

Image Reconstruction Super-Resolution

Online Learning to Rank with Features

no code implementations5 Oct 2018 Shuai Li, Tor Lattimore, Csaba Szepesvári

We introduce a new model for online ranking in which the click probability factors into an examination and attractiveness function and the attractiveness function is a linear function of a feature vector and an unknown parameter.

Learning-To-Rank online learning

S-System, Geometry, Learning, and Optimization: A Theory of Neural Networks

no code implementations27 Sep 2018 Shuai Li, Kui Jia

We present a formal measure-theoretical theory of neural networks (NN) built on {\it probability coupling theory}.

Gear Training: A new way to implement high-performance model-parallel training

no code implementations11 Jun 2018 Hao Dong, Shuai Li, Dongchang Xu, Yi Ren, Di Zhang

The training of Deep Neural Networks usually needs tremendous computing resources.

TopRank: A practical algorithm for online stochastic ranking

no code implementations NeurIPS 2018 Tor Lattimore, Branislav Kveton, Shuai Li, Csaba Szepesvari

Online learning to rank is a sequential decision-making problem where in each round the learning agent chooses a list of items and receives feedback in the form of clicks from the user.

Decision Making Learning-To-Rank +1

Offline Evaluation of Ranking Policies with Click Models

no code implementations27 Apr 2018 Shuai Li, Yasin Abbasi-Yadkori, Branislav Kveton, S. Muthukrishnan, Vishwa Vinay, Zheng Wen

We analyze our estimators and prove that they are more efficient than the estimators that do not use the structure of the click model, under the assumption that the click model holds.

Recommendation Systems

A Fusion Framework for Camouflaged Moving Foreground Detection in the Wavelet Domain

no code implementations16 Apr 2018 Shuai Li, Dinei Florencio, Wanqing Li, Yaqin Zhao, Chris Cook

Conventional methods cannot distinguish the foreground from background due to the small differences between them and thus suffer from under-detection of the camouflaged foreground objects.

Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN

11 code implementations CVPR 2018 Shuai Li, Wanqing Li, Chris Cook, Ce Zhu, Yanbo Gao

Experimental results have shown that the proposed IndRNN is able to process very long sequences (over 5000 time steps), can be used to construct very deep networks (21 layers used in the experiment) and still be trained robustly.

Language Modelling Sequential Image Classification +1

Hole Filling with Multiple Reference Views in DIBR View Synthesis

no code implementations8 Feb 2018 Shuai Li, Ce Zhu, Ming-Ting Sun

In this paper, we first examine the view interpolation with multiple reference views, demonstrating that the problem of emerging holes in a target virtual view can be greatly alleviated by making good use of other neighboring complementary views in addition to its two (commonly used) most neighboring primary views.

Online Clustering of Contextual Cascading Bandits

no code implementations23 Nov 2017 Shuai Li

We consider a new setting of online clustering of contextual cascading bandits, an online learning problem where the underlying cluster structure over users is unknown and needs to be learned from a random prefix feedback.

Online Clustering online learning

Beetle Antennae Search without Parameter Tuning (BAS-WPT) for Multi-objective Optimization

1 code implementation7 Nov 2017 Xiangyuan Jiang, Shuai Li

Beetle antennae search (BAS) is an efficient meta-heuristic algorithm inspired by foraging behaviors of beetles.

BAS: Beetle Antennae Search Algorithm for Optimization Problems

5 code implementations30 Oct 2017 Xiangyuan Jiang, Shuai Li

Meta-heuristic algorithms have become very popular because of powerful performance on the optimization problem.

Porcellio scaber algorithm (PSA) for solving constrained optimization problems

no code implementations11 Oct 2017 Yinyan Zhang, Shuai Li, Hongliang Guo

In this paper, we extend a bio-inspired algorithm called the porcellio scaber algorithm (PSA) to solve constrained optimization problems, including a constrained mixed discrete-continuous nonlinear optimization problem.

PSA: A novel optimization algorithm based on survival rules of porcellio scaber

no code implementations28 Sep 2017 Yinyan Zhang, Pei Zhang, Shuai Li

Bio-inspired algorithms such as neural network algorithms and genetic algorithms have received a significant amount of attention in both academic and engineering societies.

Foreground Detection in Camouflaged Scenes

no code implementations11 Jul 2017 Shuai Li, Dinei Florencio, Yaqin Zhao, Chris Cook, Wanqing Li

This paper proposes a texture guided weighted voting (TGWV) method which can efficiently detect foreground objects in camouflaged scenes.

A Fully Trainable Network with RNN-based Pooling

no code implementations16 Jun 2017 Shuai Li, Wanqing Li, Chris Cook, Ce Zhu, Yanbo Gao

Such a network with learnable pooling function is referred to as a fully trainable network (FTN).

Deep LSTM for Large Vocabulary Continuous Speech Recognition

no code implementations21 Mar 2017 Xu Tian, Jun Zhang, Zejun Ma, Yi He, Juan Wei, Peihao Wu, Wenchang Situ, Shuai Li, Yang Zhang

It is a competitive framework that LSTM models of more than 7 layers are successfully trained on Shenma voice search data in Mandarin and they outperform the deep LSTM models trained by conventional approach.

14 Speech Recognition +1

Lensless computational imaging through deep learning

no code implementations22 Feb 2017 Ayan Sinha, Justin Lee, Shuai Li, George Barbastathis

Deep learning has been proven to yield reliably generalizable answers to numerous classification and decision tasks.

General Classification

Akid: A Library for Neural Network Research and Production from a Dataism Approach

no code implementations3 Jan 2017 Shuai Li

The distributed computing stack handles the concurrency and communication, thus letting models be trained or deployed to a single GPU, multiple GPUs, or a distributed environment without affecting how a model is specified in the programming paradigm stack.

Distributed Computing

Automatic Discoveries of Physical and Semantic Concepts via Association Priors of Neuron Groups

no code implementations30 Dec 2016 Shuai Li, Kui Jia, Xiaogang Wang

The recent successful deep neural networks are largely trained in a supervised manner.

On Context-Dependent Clustering of Bandits

no code implementations ICML 2017 Claudio Gentile, Shuai Li, Purushottam Kar, Alexandros Karatzoglou, Evans Etrue, Giovanni Zappella

We investigate a novel cluster-of-bandit algorithm CAB for collaborative recommendation tasks that implements the underlying feedback sharing mechanism by estimating the neighborhood of users in a context-dependent manner.

Online Optimization Methods for the Quantification Problem

no code implementations13 May 2016 Purushottam Kar, Shuai Li, Harikrishna Narasimhan, Sanjay Chawla, Fabrizio Sebastiani

The estimation of class prevalence, i. e., the fraction of a population that belongs to a certain class, is a very useful tool in data analytics and learning, and finds applications in many domains such as sentiment analysis, epidemiology, etc.

Epidemiology Sentiment Analysis

Graph Clustering Bandits for Recommendation

no code implementations2 May 2016 Shuai Li, Claudio Gentile, Alexandros Karatzoglou

We investigate an efficient context-dependent clustering technique for recommender systems based on exploration-exploitation strategies through multi-armed bandits over multiple users.

Graph Clustering Multi-Armed Bandits +1

Distributed Clustering of Linear Bandits in Peer to Peer Networks

no code implementations26 Apr 2016 Nathan Korda, Balazs Szorenyi, Shuai Li

We provide two distributed confidence ball algorithms for solving linear bandit problems in peer to peer networks with limited communication capabilities.

Context-Aware Bandits

no code implementations12 Oct 2015 Shuai Li, Purushottam Kar

We propose an efficient Context-Aware clustering of Bandits (CAB) algorithm, which can capture collaborative effects.

Multi-Armed Bandits

Collaborative Filtering Bandits

no code implementations11 Feb 2015 Shuai Li, Alexandros Karatzoglou, Claudio Gentile

Our algorithm takes into account the collaborative effects that arise due to the interaction of the users with the items, by dynamically grouping users based on the items under consideration and, at the same time, grouping items based on the similarity of the clusterings induced over the users.

Collaborative Filtering News Recommendation

Online Clustering of Bandits

no code implementations31 Jan 2014 Claudio Gentile, Shuai Li, Giovanni Zappella

We introduce a novel algorithmic approach to content recommendation based on adaptive clustering of exploration-exploitation ("bandit") strategies.

Online Clustering

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