Open Access. Powered by Scholars. Published by Universities.®
Artificial Intelligence and Robotics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Machine Learning (cs.LG) (9)
- Learning systems (8)
- Machine learning (6)
- Optimization (6)
- Reinforcement learning (6)
-
- Deep learning (5)
- Stochastic systems (5)
- Artificial Intelligence (cs.AI) (4)
- Computational linguistics (4)
- Simple++ (4)
- Antennas (3)
- Artificial intelligence (3)
- Condition (3)
- Internet of things (3)
- Learn+ (3)
- Optimization and Control (math.OC) (3)
- Wireless networks (3)
- Auto encoders (2)
- Benchmarking (2)
- Classification (of information) (2)
- Classification tasks (2)
- Computer vision (2)
- Constrained optimization (2)
- Design (2)
- Distributed optimization (2)
- Feature extraction (2)
- Feature selection (2)
- Federated learning (2)
- Forecasting (2)
- Geometry (2)
Articles 31 - 60 of 86
Full-Text Articles in Artificial Intelligence and Robotics
Zeroth-Order Hard-Thresholding: Gradient Error Vs. Expansivity, William De Vazelhes, Hualin Zhang, Huimin Wu, Xiao Tong Yuan, Bin Gu
Zeroth-Order Hard-Thresholding: Gradient Error Vs. Expansivity, William De Vazelhes, Hualin Zhang, Huimin Wu, Xiao Tong Yuan, Bin Gu
Machine Learning Faculty Publications
ℓ0 constrained optimization is prevalent in machine learning, particularly for high-dimensional problems, because it is a fundamental approach to achieve sparse learning. Hard-thresholding gradient descent is a dominant technique to solve this problem. However, first-order gradients of the objective function may be either unavailable or expensive to calculate in a lot of real-world problems, where zeroth-order (ZO) gradients could be a good surrogate. Unfortunately, whether ZO gradients can work with the hard-thresholding operator is still an unsolved problem. To solve this puzzle, in this paper, we focus on the ℓ0 constrained black-box stochastic optimization problems, and propose a new stochastic …
Zeroth-Order Negative Curvature Finding: Escaping Saddle Points Without Gradients, Hualin Zhang, Huan Xiong, Bin Gu
Zeroth-Order Negative Curvature Finding: Escaping Saddle Points Without Gradients, Hualin Zhang, Huan Xiong, Bin Gu
Machine Learning Faculty Publications
We consider escaping saddle points of nonconvex problems where only the function evaluations can be accessed. Although a variety of works have been proposed, the majority of them require either second or first-order information, and only a few of them have exploited zeroth-order methods, particularly the technique of negative curvature finding with zeroth-order methods which has been proven to be the most efficient method for escaping saddle points. To fill this gap, in this paper, we propose two zeroth-order negative curvature finding frameworks that can replace Hessian-vector product computations without increasing the iteration complexity. We apply the proposed frameworks to …
Hyperfast Second-Order Local Solvers For Efficient Statistically Preconditioned Distributed Optimization, Pavel Dvurechensky, Dmitry Kamzolov, Aleksandr Lukashevich, Soomin Lee, Erik Ordentlich, César A. Uribe, Alexander Gasnikov
Hyperfast Second-Order Local Solvers For Efficient Statistically Preconditioned Distributed Optimization, Pavel Dvurechensky, Dmitry Kamzolov, Aleksandr Lukashevich, Soomin Lee, Erik Ordentlich, César A. Uribe, Alexander Gasnikov
Machine Learning Faculty Publications
Statistical preconditioning enables fast methods for distributed large-scale empirical risk minimization problems. In this approach, multiple worker nodes compute gradients in parallel, which are then used by the central node to update the parameter by solving an auxiliary (preconditioned) smaller-scale optimization problem. The recently proposed Statistically Preconditioned Accelerated Gradient (SPAG) method [1] has complexity bounds superior to other such algorithms but requires an exact solution for computationally intensive auxiliary optimization problems at every iteration. In this paper, we propose an Inexact SPAG (InSPAG) and explicitly characterize the accuracy by which the corresponding auxiliary subproblem needs to be solved to guarantee …
Lemurs Optimizer: A New Metaheuristic Algorithm For Global Optimization, Ammar Kamal Abasi, Sharif Naser Makhadmeh, Mohammed Azmi Al-Betar, Osama Ahmad Alomari, Mohammed A. Awadallah, Zaid Abdi Alkareem Alyasseri, Iyad Abu Doush, Ashraf Elnagar, Eman H. Alkhammash, Myriam Hadjouni
Lemurs Optimizer: A New Metaheuristic Algorithm For Global Optimization, Ammar Kamal Abasi, Sharif Naser Makhadmeh, Mohammed Azmi Al-Betar, Osama Ahmad Alomari, Mohammed A. Awadallah, Zaid Abdi Alkareem Alyasseri, Iyad Abu Doush, Ashraf Elnagar, Eman H. Alkhammash, Myriam Hadjouni
Machine Learning Faculty Publications
The Lemur Optimizer (LO) is a novel nature-inspired algorithm we propose in this paper. This algorithm’s primary inspirations are based on two pillars of lemur behavior: leap up and dance hub. These two principles are mathematically modeled in the optimization context to handle local search, exploitation, and exploration search concepts. The LO is first benchmarked on twenty-three standard optimization functions. Additionally, the LO is used to solve three real-world problems to evaluate its performance and effectiveness. In this direction, LO is compared to six well-known algorithms: Salp Swarm Algorithm (SSA), Artificial Bee Colony (ABC), Sine Cosine Algorithm (SCA), Bat Algorithm …
Stochastic Trajectory Prediction Via Motion Indeterminacy Diffusion, Tianpei Gu, Guangyi Chen, Junlong Li, Chunze Lin, Yongming Rao, Jie Zhou, Jiwen Lu
Stochastic Trajectory Prediction Via Motion Indeterminacy Diffusion, Tianpei Gu, Guangyi Chen, Junlong Li, Chunze Lin, Yongming Rao, Jie Zhou, Jiwen Lu
Machine Learning Faculty Publications
Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states. Unlike existing stochastic trajectory prediction methods which usually use a latent variable to represent multi-modality, we explicitly simulate the process of human motion variation from indeterminate to determinate. In this paper, we present a new framework to formulate the trajectory prediction task as a reverse process of motion indeterminacy diffusion (MID), in which we progressively discard indeterminacy from all the walkable areas until reaching the desired trajectory. This process is learned with a parameterized Markov chain conditioned by …
Maximum Spatial Perturbation Consistency For Unpaired Image-To-Image Translation, Yanwu Xu, Shaoan Xie, Wenhao Wu, Kun Zhang, Mingming Gong, Kayhan Batmanghelich
Maximum Spatial Perturbation Consistency For Unpaired Image-To-Image Translation, Yanwu Xu, Shaoan Xie, Wenhao Wu, Kun Zhang, Mingming Gong, Kayhan Batmanghelich
Machine Learning Faculty Publications
Unpaired image-to-image translation (I2I) is an ill-posed problem, as an infinite number of translation functions can map the source domain distribution to the target distribution. Therefore, much effort has been put into designing suitable constraints, e.g., cycle consistency (CycleGAN), geometry consistency (GCGAN), and contrastive learning-based constraints (CUTGAN), that help better pose the problem. However, these well-known constraints have limitations: (1) they are either too restrictive or too weak for specific I2I tasks; (2) these methods result in content distortion when there is a significant spatial variation between the source and target domains. This paper proposes a universal regularization technique called …
Learning Hierarchical Metrical Structure Beyond Measures, Junyan Jiang, Daniel Chin, Yixiao Zhang, Gus Xia
Learning Hierarchical Metrical Structure Beyond Measures, Junyan Jiang, Daniel Chin, Yixiao Zhang, Gus Xia
Machine Learning Faculty Publications
Music contains hierarchical structures beyond beats and measures. While hierarchical structure annotations are helpful for music information retrieval and computer musicology, such annotations are scarce in current digital music databases. In this paper, we explore a data-driven approach to automatically extract hierarchical metrical structures from scores. We propose a new model with a Temporal Convolutional Network-Conditional Random Field (TCN-CRF) architecture. Given a symbolic music score, our model takes in an arbitrary number of voices in a beat-quantized form, and predicts a 4-level hierarchical metrical structure from downbeat-level to section-level. We also annotate a dataset using RWC-POP MIDI files to facilitate …
Artificial Intelligence-Driven Design Of Fuel Mixtures, Nursulu Kuzhagaliyeva, Samuel Horváth, John Williams, Andre Nicolle, S. Mani Sarathy
Artificial Intelligence-Driven Design Of Fuel Mixtures, Nursulu Kuzhagaliyeva, Samuel Horváth, John Williams, Andre Nicolle, S. Mani Sarathy
Machine Learning Faculty Publications
High-performance fuel design is imperative to achieve cleaner burning and high-efficiency engine systems. We introduce a data-driven artificial intelligence (AI) framework to design liquid fuels exhibiting tailor-made properties for combustion engine applications to improve efficiency and lower carbon emissions. The fuel design approach is a constrained optimization task integrating two parts: (i) a deep learning (DL) model to predict the properties of pure components and mixtures and (ii) search algorithms to efficiently navigate in the chemical space. Our approach presents the mixture-hidden vector as a linear combination of each single component’s vectors in each blend and incorporates it into the …
Beat Transformer: Demixed Beat And Downbeat Tracking With Dilated Self-Attention, Jingwei Zhao, Gus Xia, Ye Wang
Beat Transformer: Demixed Beat And Downbeat Tracking With Dilated Self-Attention, Jingwei Zhao, Gus Xia, Ye Wang
Machine Learning Faculty Publications
We propose Beat Transformer, a novel Transformer encoder architecture for joint beat and downbeat tracking. Different from previous models that track beats solely based on the spectrogram of an audio mixture, our model deals with demixed spectrograms with multiple instrument channels. This is inspired by the fact that humans perceive metrical structures from richer musical contexts, such as chord progression and instrumentation. To this end, we develop a Transformer model with both time-wise attention and instrument-wise attention to capture deep-buried metrical cues. Moreover, our model adopts a novel dilated self-attention mechanism, which achieves powerful hierarchical modelling with only linear complexity. …
Domain Adversarial Training On Conditional Variational Auto-Encoder For Controllable Music Generation, Jingwei Zhao, Gus Xia, Ye Wang
Domain Adversarial Training On Conditional Variational Auto-Encoder For Controllable Music Generation, Jingwei Zhao, Gus Xia, Ye Wang
Machine Learning Faculty Publications
The variational auto-encoder has become a leading framework for symbolic music generation, and a popular research direction is to study how to effectively control the generation process. A straightforward way is to control a model using different conditions during inference. However, in music practice, conditions are usually sequential (rather than simple categorical labels), involving rich information that overlaps with the learned representation. Consequently, the decoder gets confused about whether to “listen to” the latent representation or the condition, and sometimes just ignores the condition. To solve this problem, we leverage domain adversarial training to disentangle the representation from condition cues …
Decentralized Personalized Federated Learning: Lower Bounds And Optimal Algorithm For All Personalization Modes, Abdurakhmon Sadiev, Ekaterina Borodich, Aleksandr Beznosikov, Darina Dvinskikh, Saveliy Chezhegov, Rachael Tappenden, Martin Takac, Alexander Gasnikov
Decentralized Personalized Federated Learning: Lower Bounds And Optimal Algorithm For All Personalization Modes, Abdurakhmon Sadiev, Ekaterina Borodich, Aleksandr Beznosikov, Darina Dvinskikh, Saveliy Chezhegov, Rachael Tappenden, Martin Takac, Alexander Gasnikov
Machine Learning Faculty Publications
This paper considers the problem of decentralized, personalized federated learning. For centralized personalized federated learning, a penalty that measures the deviation from the local model and its average, is often added to the objective function. However, in a decentralized setting this penalty is expensive in terms of communication costs, so here, a different penalty — one that is built to respect the structure of the underlying computational network — is used instead. We present lower bounds on the communication and local computation costs for this problem formulation and we also present provably optimal methods for decentralized personalized federated learning. Numerical …
Accomontage2: A Complete Harmonization And Accompaniment Arrangement System, Li Yi, Haochen Hu, Jingwei Zhao, Gus Xia
Accomontage2: A Complete Harmonization And Accompaniment Arrangement System, Li Yi, Haochen Hu, Jingwei Zhao, Gus Xia
Machine Learning Faculty Publications
We propose AccoMontage2, a system capable of doing full-length song harmonization and accompaniment arrangement based on a lead melody. Following AccoMontage, this study focuses on generating piano arrangements for popular/folk songs and it carries on the generalized template-based retrieval method. The novelties of this study are twofold. First, we invent a harmonization module (which AccoMontage does not have). This module generates structured and coherent full-length chord progression by optimizing and balancing three loss terms: a micro-level loss for note-wise dissonance, a meso-level loss for phrase-template matching, and a macro-level loss for full piece coherency. Second, we develop a graphical user …
Negational Symmetry Of Quantum Neural Networks For Binary Pattern Classification, Nanqing Dong, Michael Kampffmeyer, Irina Voiculescu, Eric P. Xing
Negational Symmetry Of Quantum Neural Networks For Binary Pattern Classification, Nanqing Dong, Michael Kampffmeyer, Irina Voiculescu, Eric P. Xing
Machine Learning Faculty Publications
Although quantum neural networks (QNNs) have shown promising results in solving simple machine learning tasks recently, the behavior of QNNs in binary pattern classification is still underexplored. In this work, we find that QNNs have an Achilles’ heel in binary pattern classification. To illustrate this point, we provide a theoretical insight into the properties of QNNs by presenting and analyzing a new form of symmetry embedded in a family of QNNs with full entanglement, which we term negational symmetry. Due to negational symmetry, QNNs can not differentiate between a quantum binary signal and its negational counterpart. We empirically evaluate the …
Truncated Matrix Power Iteration For Differentiable Dag Learning, Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Ehsan M. Abbasnejad, Mingming Gong, Kun Zhang, Javen Qinfeng Shi
Truncated Matrix Power Iteration For Differentiable Dag Learning, Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Ehsan M. Abbasnejad, Mingming Gong, Kun Zhang, Javen Qinfeng Shi
Machine Learning Faculty Publications
Recovering underlying Directed Acyclic Graph structures (DAG) from observational data is highly challenging due to the combinatorial nature of the DAG-constrained optimization problem. Recently, DAG learning has been cast as a continuous optimization problem by characterizing the DAG constraint as a smooth equality one, generally based on polynomials over adjacency matrices. Existing methods place very small coefficients on high-order polynomial terms for stabilization, since they argue that large coefficients on the higher-order terms are harmful due to numeric exploding. On the contrary, we discover that large coefficients on higher-order terms are beneficial for DAG learning, when the spectral radiuses of …
Exploiting Higher-Order Derivatives In Convex Optimization Methods, Dmitry Kamzolov, Alexander Gasnikov, Pavel Dvurechensky, Artem Agafonov, Martin Takac
Exploiting Higher-Order Derivatives In Convex Optimization Methods, Dmitry Kamzolov, Alexander Gasnikov, Pavel Dvurechensky, Artem Agafonov, Martin Takac
Machine Learning Faculty Publications
Exploiting higher-order derivatives in convex optimization is known at least since 1970’s. In each iteration higher-order (also called tensor) methods minimize a regularized Taylor expansion of the objective function, which leads to faster convergence rates if the corresponding higher-order derivative is Lipschitz-continuous. Recently a series of lower iteration complexity bounds for such methods were proved, and a gap between upper an lower complexity bounds was revealed. Moreover, it was shown that such methods can be implementable since the appropriately regularized Taylor expansion of a convex function is also convex and, thus, can be minimized in polynomial time. Only very recently …
Sr-Dcsk Cooperative Communication System With Code Index Modulation: A New Design For 6g New Radios, Yi Fang, Wang Chen, Pingping Chen, Yiwei Tao, Mohsen Guizani
Sr-Dcsk Cooperative Communication System With Code Index Modulation: A New Design For 6g New Radios, Yi Fang, Wang Chen, Pingping Chen, Yiwei Tao, Mohsen Guizani
Machine Learning Faculty Publications
This paper proposes a high-throughput short reference differential chaos shift keying cooperative communication system with the aid of code index modulation, referred to as CIM-SR-DCSK-CC system. In the proposed CIM-SR-DCSK-CC system, the source transmits information bits to both the relay and destination in the first time slot, while the relay not only forwards the source information bits but also sends new information bits to the destination in the second time slot. To be specific, the relay employs an N-order Walsh code to carry additional log2N information bits, which are superimposed onto the SR-DCSK signal carrying the decoded source information bits. …
Interpreting Song Lyrics With An Audio-Informed Pre-Trained Language Model, Yixiao Zhang, Junyan Jiang, Gus Xia, Simon Dixon
Interpreting Song Lyrics With An Audio-Informed Pre-Trained Language Model, Yixiao Zhang, Junyan Jiang, Gus Xia, Simon Dixon
Machine Learning Faculty Publications
Lyric interpretations can help people understand songs and their lyrics quickly, and can also make it easier to manage, retrieve and discover songs efficiently from the growing mass of music archives. In this paper we propose BART-fusion, a novel model for generating lyric interpretations from lyrics and music audio that combines a large-scale pre-trained language model with an audio encoder. We employ a cross-modal attention module to incorporate the audio representation into the lyrics representation to help the pre-trained language model understand the song from an audio perspective, while preserving the language model’s original generative performance. We also release the …
Fdrl Approach For Association And Resource Allocation In Multi-Uav Air-To-Ground Iomt Network, Abegaz Mohammed, Aiman Erbad, Hayla Nahom, Abdullatif Albaseer, Mohammed Abdallah, Mohsen Guizani
Fdrl Approach For Association And Resource Allocation In Multi-Uav Air-To-Ground Iomt Network, Abegaz Mohammed, Aiman Erbad, Hayla Nahom, Abdullatif Albaseer, Mohammed Abdallah, Mohsen Guizani
Machine Learning Faculty Publications
In 6G networks, unmanned aerial vehicles (UAVs) can serve as aerial flying base stations (AFBS) with aerial mobile edge computing (AMEC) server capabilities. AFBS is an increasingly popular solution for delivering time-sensitive applications, extending network coverage, and assisting ground base stations in the healthcare systems for remote areas with limited infrastructure. Furthermore, the UAVs are deployed in the healthcare system to support the Internet of medical things (IoMT) devices in data collection, medical equipment distribution, and providing smart services. However, ensuring the privacy and security of patients’ data with the limited UAV resources is a major challenge. In this paper, …
Reconfigurable Intelligent Surfaces And Capacity Optimization: A Large System Analysis, Aris L. Moustakas, George C. Alexandropoulos, Mérouane Debbah
Reconfigurable Intelligent Surfaces And Capacity Optimization: A Large System Analysis, Aris L. Moustakas, George C. Alexandropoulos, Mérouane Debbah
Machine Learning Faculty Publications
Reconfigurable Intelligent Surfaces (RISs), comprising large numbers of low-cost and almost passive metamaterials with tunable reflection properties, have been recently proposed as an enabling technology for programmable wireless propagation environments. In this paper, we present asymptotic closed-form expressions for the mean and variance of the mutual information metric for a multi-antenna transmitter-receiver pair in the presence of multiple RISs, using methods from statistical physics. While nominally valid in the large system limit, we show that the derived Gaussian approximation for the mutual information can be quite accurate, even for modest-sized antenna arrays and metasurfaces. The above results are particularly useful …
A Multi-Dimensional Matrix Pencil-Based Channel Prediction Method For Massive Mimo With Mobility, Weidong Li, Haifan Yin, Ziao Qin, Yandi Cao, Mérouane Debbah
A Multi-Dimensional Matrix Pencil-Based Channel Prediction Method For Massive Mimo With Mobility, Weidong Li, Haifan Yin, Ziao Qin, Yandi Cao, Mérouane Debbah
Machine Learning Faculty Publications
This paper addresses the mobility problem in massive multiple-input multiple-output systems, which leads to significant performance losses in the practical deployment of the fifth generation mobile communication networks. We propose a novel channel prediction method based on multi-dimensional matrix pencil (MDMP), which estimates the path parameters by exploiting the angular-frequency-domain and angular-timedomain structures of the wideband channel. The MDMP method also entails a novel path pairing scheme to pair the delay and Doppler, based on the super-resolution property of the angle estimation. Our method is able to deal with the realistic constraint of time-varying path delays introduced by user movements, …
Meta-Detr: Image-Level Few-Shot Detection With Inter-Class Correlation Exploitation, Gongjie Zhang, Zhipeng Luo, Kaiwen Cui, Shijian Lu, Eric P. Xing
Meta-Detr: Image-Level Few-Shot Detection With Inter-Class Correlation Exploitation, Gongjie Zhang, Zhipeng Luo, Kaiwen Cui, Shijian Lu, Eric P. Xing
Machine Learning Faculty Publications
Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks. Despite its success, the said paradigm is still constrained by several factors, such as (i) low-quality region proposals for novel classes and (ii) negligence of the inter-class correlation among different classes. Such limitations hinder the generalization of base-class knowledge for the detection of novel-class objects. In this work, we design Meta-DETR, which (i) is the first image-level few-shot detector, and (ii) introduces a novel inter-class correlational meta-learning strategy to capture and leverage the correlation among different classes for robust and accurate few-shot object detection. Meta-DETR works …
Semantic-Aligned Matching For Enhanced Detr Convergence And Multi-Scale Feature Fusion, Gongjie Zhang, Zhipeng Luo, Yingchen Yu, Jiaxing Huang, Kaiwen Cui, Shijian Lu, Eric Xing
Semantic-Aligned Matching For Enhanced Detr Convergence And Multi-Scale Feature Fusion, Gongjie Zhang, Zhipeng Luo, Yingchen Yu, Jiaxing Huang, Kaiwen Cui, Shijian Lu, Eric Xing
Machine Learning Faculty Publications
The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection. However, DETR suffers from slow training convergence, which hinders its applicability to various detection tasks. We observe that DETR's slow convergence is largely attributed to the difficulty in matching object queries to relevant regions due to the unaligned semantics between object queries and encoded image features. With this observation, we design Semantic-Aligned-Matching DETR++ (SAM-DETR++) to accelerate DETR's convergence and improve detection performance. The core of SAM-DETR++ is a plug-andplay module that projects object queries and encoded image features into the same feature embedding space, where …
Towards Smart City Security: Violence And Weaponized Violence Detection Using Dcnn, Toluwani Aremu, Li Zhiyuan, Reem Alameeri, Moayad Aloqaily, Mohsen Guizani
Towards Smart City Security: Violence And Weaponized Violence Detection Using Dcnn, Toluwani Aremu, Li Zhiyuan, Reem Alameeri, Moayad Aloqaily, Mohsen Guizani
Machine Learning Faculty Publications
In this ever connected society, CCTVs have had a pivotal role in enforcing safety and security of the citizens by recording unlawful activities for the authorities to take actions. In a smart city context, using Deep Convolutional Neural Networks (DCNN) to detection violence and weaponized violence from CCTV videos will provide an additional layer of security by ensuring real-time detection around the clock. In this work, we introduced a new specialised dataset by gathering real CCTV footage of both weaponized and non-weaponized violence as well as non-violence videos from YouTube. We also proposed a novel approach in merging consecutive video …
Green, Quantized Federated Learning Over Wireless Networks: An Energy-Efficient Design, Minsu Kim, Walid Saad, Mohammad Mozaffari, Mérouane Debbah
Green, Quantized Federated Learning Over Wireless Networks: An Energy-Efficient Design, Minsu Kim, Walid Saad, Mohammad Mozaffari, Mérouane Debbah
Machine Learning Faculty Publications
The practical deployment of federated learning (FL) over wireless networks requires balancing energy efficiency and convergence time due to the limited available resources of devices. Prior art on FL often trains deep neural networks (DNNs) to achieve high accuracy and fast convergence using 32 bits of precision level. However, such scenarios will be impractical for resource-constrained devices since DNNs typically have high computational complexity and memory requirements. Thus, there is a need to reduce the precision level in DNNs to reduce the energy expenditure. In this paper, a green-quantized FL framework, which represents data with a finite precision level in …
Robustar: Interactive Toolbox Supporting Precise Data Annotation For Robust Vision Learning, Chonghan Chen, Haohan Wang, Leyang Hu, Yuhao Zhang, Shuguang Lyu, Jingcheng Wu, Xinnuo Li, Linjing Sun, Eric Xing
Robustar: Interactive Toolbox Supporting Precise Data Annotation For Robust Vision Learning, Chonghan Chen, Haohan Wang, Leyang Hu, Yuhao Zhang, Shuguang Lyu, Jingcheng Wu, Xinnuo Li, Linjing Sun, Eric Xing
Machine Learning Faculty Publications
We introduce the initial release of our software Robustar, which aims to improve the robustness of vision classification machine learning models through a data-driven perspective. Building upon the recent understanding that the lack of machine learning model’s robustness is the tendency of the model’s learning of spurious features, we aim to solve this problem from its root at the data perspective by removing the spurious features from the data before training. In particular, we introduce a software that helps the users to better prepare the data for training image classification models by allowing the users to annotate the spurious features …
Sdq: Stochastic Differentiable Quantization With Mixed Precision, Xijie Huang, Zhiqiang Shen, Shichao Li, Zechun Liu, Xianghong Hu, Jeffry Wicaksana, Eric Xing, Kwang Ting Cheng
Sdq: Stochastic Differentiable Quantization With Mixed Precision, Xijie Huang, Zhiqiang Shen, Shichao Li, Zechun Liu, Xianghong Hu, Jeffry Wicaksana, Eric Xing, Kwang Ting Cheng
Machine Learning Faculty Publications
In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitwidth arithmetic operations, recent research on mixed precision quantization (MPQ) begins to fully leverage the capacity of representation by searching optimized bitwidths for different layers and modules in a network. However, previous studies mainly search the MPQ strategy in a costly scheme using reinforcement learning, neural architecture search, etc., or simply utilize partial prior knowledge for bitwidth assignment, which might be biased on locality of information and is sub-optimal. In this work, we present …
Action-Sufficient State Representation Learning For Control With Structural Constraints, Biwei Huang, Chaochao Lu, Liu Leqi, Josã© Miguel Hernã¡Ndez-Lobato, Clark Glymour, Bernhard Schã¶Lkopf, Kun Zhang
Action-Sufficient State Representation Learning For Control With Structural Constraints, Biwei Huang, Chaochao Lu, Liu Leqi, Josã© Miguel Hernã¡Ndez-Lobato, Clark Glymour, Bernhard Schã¶Lkopf, Kun Zhang
Machine Learning Faculty Publications
Perceived signals in real-world scenarios are usually high-dimensional and noisy, and finding and using their representation that contains essential and sufficient information required by downstream decision-making tasks will help improve computational efficiency and generalization ability in the tasks. In this paper, we focus on partially observable environments and propose to learn a minimal set of state representations that capture sufficient information for decision-making, termed Action-Sufficient state Representations (ASRs). We build a generative environment model for the structural relationships among variables in the system and present a principled way to characterize ASRs based on structural constraints and the goal of maximizing …
Gradient-Free Method For Heavily Constrained Nonconvex Optimization, Wanli Shi, Hongchang Gao, Bin Gu
Gradient-Free Method For Heavily Constrained Nonconvex Optimization, Wanli Shi, Hongchang Gao, Bin Gu
Machine Learning Faculty Publications
Zeroth-order (ZO) method has been shown to be a powerful method for solving the optimization problem where explicit expression of the gradients is difficult or infeasible to obtain. Recently, due to the practical value of the constrained problems, a lot of ZO Frank-Wolfe or projected ZO methods have been proposed. However, in many applications, we may have a very large number of nonconvex white/black-box constraints, which makes the existing zeroth-order methods extremely inefficient (or even not working) since they need to inquire function value of all the constraints and project the solution to the complicated feasible set. In this paper, …
Identification Of Linear Non-Gaussian Latent Hierarchical Structure, Feng Xie, Biwei Huang, Zhengming Chen, Yangbo He, Zhi Geng, Kun Zhang
Identification Of Linear Non-Gaussian Latent Hierarchical Structure, Feng Xie, Biwei Huang, Zhengming Chen, Yangbo He, Zhi Geng, Kun Zhang
Machine Learning Faculty Publications
Traditional causal discovery methods mainly focus on estimating causal relations among measured variables, but in many real-world problems, such as questionnaire-based psychometric studies, measured variables are generated by latent variables that are causally related. Accordingly, this paper investigates the problem of discovering the hidden causal variables and estimating the causal structure, including both the causal relations among latent variables and those between latent and measured variables. We relax the frequently-used measurement assumption and allow the children of latent variables to be latent as well, and hence deal with a specific type of latent hierarchical causal structure. In particular, we define …
Dynamic Prototype Convolution Network For Few-Shot Semantic Segmentation, Jie Liu, Yanqi Bao, Guo-Sen Xie, Huan Xiong, Jan-Jakob Sonke, Efstratios Gavves
Dynamic Prototype Convolution Network For Few-Shot Semantic Segmentation, Jie Liu, Yanqi Bao, Guo-Sen Xie, Huan Xiong, Jan-Jakob Sonke, Efstratios Gavves
Machine Learning Faculty Publications
The key challenge for few-shot semantic segmentation (FSS) is how to tailor a desirable interaction among sup-port and query features and/or their prototypes, under the episodic training scenario. Most existing FSS methods im-plement such support/query interactions by solely leveraging plain operations - e.g., cosine similarity and feature concatenation - for segmenting the query objects. How-ever, these interaction approaches usually cannot well capture the intrinsic object details in the query images that are widely encountered in FSS, e.g., if the query object to be segmented has holes and slots, inaccurate segmentation al-most always happens. To this end, we propose a dynamic …