Publications (98)
On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
Yicheng Li, Zixiong Yu, Guhan Chen +1
In this paper, we provide a strategy to determine the eigenvalue decay rate (EDR) of a large class of kernel functions defined on a general domain rather than . This…
On the Pinsker bound of inner product kernel regression in large dimensions
Weihao Lu, Jialin Ding, Haobo Zhang +1
Building on recent studies of large-dimensional kernel regression, particularly those involving inner product kernels on the sphere , we investigate the Pinsker bou…
On the Structural Dimension of Sliced Inverse Regression
Dongming Huang, Songtao Tian, Qian Lin
In this work, we address the longstanding puzzle that Sliced Inverse Regression (SIR) often performs poorly for sufficient dimension reduction when the structural dimension (th…
Scaling Distributed Transaction Processing and Recovery based on Dependency Logging
Chang Yao, Meihui Zhang, Qian Lin +2
DGCC protocol has been shown to achieve good performance on multi-core in-memory system. However, distributed transactions complicate the dependency resolution, and therefore, an e…
Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions
Haobo Zhang, Yicheng Li, Weihao Lu +1
Motivated by the studies of neural networks (e.g.,the neural tangent kernel theory), we perform a study on the large-dimensional behavior of kernel ridge regression (KRR) where the…
Implicit Safety Alignment from Crowd Preferences
Qian Lin, Daniel S. Brown
Reinforcement Learning from Human Feedback (RLHF) can reveal implicit objectives such as safety considerations that go beyond task completion. In this work, we focus on the common…
Collective state measurement of mesoscopic ensembles with single-atom resolution
Hao Zhang, Robert McConnell, Senka Äuk +4
For mesoscopic ensembles containing 100 or more atoms we measure the total atom number and the number of atoms in a specific hyperfine state with single-atom resolution. The measur…
A BSDE approach to Nash equilibrium payoffs for stochastic differential games with nonlinear cost functionals
Qian Lin
In this paper, we study Nash equilibrium payoffs for nonzero-sum stochastic differential games via the theory of backward stochastic differential equations. We obtain an existence…
Neural Tangent Kernel of Neural Networks with Loss Informed by Differential Operators
Weiye Gan, Yicheng Li, Qian Lin +1
Spectral bias is a significant phenomenon in neural network training and can be explained by neural tangent kernel (NTK) theory. In this work, we develop the NTK theory for deep ne…
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
Hao Kong, Di Liu, Shuo Huai +5
Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks. However, the prohibitive computational cost of CNNs hinders the deployment…
Low-Temperature Eutectic Synthesis of PtTe2 with Weak Antilocalization and Controlled Layer Thinning
Song Hao, Junwen Zeng, Tao Xu +20
Metallic transition metal dichalcogenides (TMDs) have exhibited various exotic physical properties and hold the promise of novel optoelectronic and topological devices applications…
Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems
Shuo Huai, Di Liu, Hao Kong +5
Federated Learning (FL) empowers multiple clients to collaboratively learn a model, enlarging the training data of each client for high accuracy while protecting data privacy. Howe…
Emotion Recognition Using Convolutional Neural Networks
Shaoyuan Xu, Yang Cheng, Qian Lin +1
Emotion has an important role in daily life, as it helps people better communicate with and understand each other more efficiently. Facial expressions can be classified into 7 cate…
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
Guhan Chen, Yicheng Li, Qian Lin
This paper aims to discuss the impact of random initialization of neural networks in the neural tangent kernel (NTK) theory, which is ignored by most recent works in the NTK theory…
Object-Level Representation Learning for Few-Shot Image Classification
Liangqu Long, Wei Wang, Jun Wen +3
Few-shot learning that trains image classifiers over few labeled examples per category is a challenging task. In this paper, we propose to exploit an additional big dataset with di…
Backward doubly stochastic differential equations with weak assumptions on the coefficients
Qian Lin
In this paper, we deal with one dimensional backward doubly stochastic differential equations (BDSDEs) where the coefficient is left Lipschitz in y (may be discontinuous) and unifo…
Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization
Zongkai Liu, Qian Lin, Chao Yu +4
Offline Multi-Agent Reinforcement Learning (MARL) is an emerging field that aims to learn optimal multi-agent policies from pre-collected datasets. Compared to single-agent case, m…
On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay
Yicheng Li, Haobo Zhang, Qian Lin
The widely observed 'benign overfitting phenomenon' in the neural network literature raises the challenge to the 'bias-variance trade-off' doctrine in the statistical learning theo…
Generalization Ability of Wide Neural Networks on
Jianfa Lai, Manyun Xu, Rui Chen +1
We perform a study on the generalization ability of the wide two-layer ReLU neural network on . We first establish some spectral properties of the neural tangent kernel…
Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay
Yicheng Li, Weiye Gan, Zuoqiang Shi +1
The generalization error curve of certain kernel regression method aims at determining the exact order of generalization error with various source condition, noise level and choice…
Optimal Rate of Kernel Regression in Large Dimensions
Weihao Lu, Haobo Zhang, Yicheng Li +2
We perform a study on kernel regression for large-dimensional data (where the sample size is polynomially depending on the dimension of the samples, i.e., fo…
Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories
Haobo Zhang, Jianfa Lai, Yicheng Li +2
A primary advantage of neural networks lies in their feature learning characteristics, which is challenging to theoretically analyze due to the complexity of their training dynamic…
Hyperbolic Weyl point in reciprocal chiral metamaterial
Meng Xiao, Qian Lin, Shanhui Fan
We report the existence of Weyl points in a class of non-central symmetric metamaterials, which has time reversal symmetry, but does not have inversion symmetry due to chiral coupl…
On consistency and sparsity for sliced inverse regression in high dimensions
Qian Lin, Zhigen Zhao, Jun S. Liu
We provide here a framework to analyze the phase transition phenomenon of slice inverse regression (SIR), a supervised dimension reduction technique introduced by \cite{Li:1991}. U…
Synthetic space with arbitrary dimensions in a few rings undergoing dynamic modulation
Luqi Yuan, Meng Xiao, Qian Lin +1
We show that a single ring resonator undergoing dynamic modulation can be used to create a synthetic space with an arbitrary dimension. In such a system the phases of the modulatio…
Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware
Hao Kong, Di Liu, Shuo Huai +5
Scaling down the resolution of input images can greatly reduce the computational overhead of convolutional neural networks (CNNs), which is promising for edge AI. However, as an im…
Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization
Shuo Huai, Di Liu, Hao Kong +4
Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers. Deciding the number of neurons during th…
On Hardware-Aware Design and Optimization of Edge Intelligence
Shuo Huai, Hao Kong, Xiangzhong Luo +5
Edge intelligence systems, the intersection of edge computing and artificial intelligence (AI), are pushing the frontier of AI applications. However, the complexity of deep learnin…
Direction-Dependent Parity-Time Phase Transition and Non-Reciprocal Directional Amplification with Dynamic Gain-Loss Modulation
Alex Y. Song, Yu Shi, Qian Lin +1
We show that a dynamic gain-loss modulation in an optical structure can lead to a direction-dependent parity-time (PT) phase transition. The phase transition can be made thresholdl…
Communication-efficient Decentralized Machine Learning over Heterogeneous Networks
Pan Zhou, Qian Lin, Dumitrel Loghin +3
In the last few years, distributed machine learning has been usually executed over heterogeneous networks such as a local area network within a multi-tenant cluster or a wide area…
FedTR: Federated Learning Framework with Transfer Learning for Industrial Visual Inspection
Vikash Sathiamoorthy, Shuo Huai, Hao Kong +7
Federated learning (FL) is a collaborative learning scheme to train deep learning models, where collaborating parties can consolidate their models without sharing local data with o…
Representation of G-martingales as stochastic integrals with respect to the G-Brownian motion
Qian Lin
The objective of this paper is to derive a representation of symmetric G-martingales as stochastic integrals with respect to the G-Brownian motion. For this end, we first study som…
Quadratic Deformations of Lie-Poisson Structures
Qian Lin, Zhangju Liu, Yunhe Sheng
In this letter, first we give a decomposition for any Lie-Poisson structure associated to the modular vector. In particular, splits into two compatible Lie-Poisson st…
The Blessing and the Curse of the Noise behind Facial Landmark Annotations
Xiaoyu Xiang, Yang Cheng, Shaoyuan Xu +2
The evolving algorithms for 2D facial landmark detection empower people to recognize faces, analyze facial expressions, etc. However, existing methods still encounter problems of u…
Randomization Inference for Peer Effects
Xinran Li, Peng Ding, Qian Lin +2
Many previous causal inference studies require no interference, that is, the potential outcomes of a unit do not depend on the treatments of other units. However, this no-interfere…
Optimal consumption and portfolio choice with ambiguity
Qian Lin, Frank Riedel
We consider optimal consumption and portfolio choice in the presence of Knightian uncertainty in continuous-time. We embed the problem into the new framework of stochastic calculus…
On the Saturation Effects of Spectral Algorithms in Large Dimensions
Weihao Lu, Haobo Zhang, Yicheng Li +1
The saturation effects, which originally refer to the fact that kernel ridge regression (KRR) fails to achieve the information-theoretical lower bound when the regression function…
Generalization Ability of Wide Residual Networks
Jianfa Lai, Zixiong Yu, Songtao Tian +1
In this paper, we study the generalization ability of the wide residual network on with the ReLU activation function. We first show that as the width $m\rightarr…
Diagonal Over-parameterization in Reproducing Kernel Hilbert Spaces as an Adaptive Feature Model: Generalization and Adaptivity
Yicheng Li, Qian Lin
This paper introduces a diagonal adaptive kernel model that dynamically learns kernel eigenvalues and output coefficients simultaneously during training. Unlike fixed-kernel method…
Experimental demonstration of dynamical input isolation in nonadiabatically modulated photonic cavities
Avik Dutt, Momchil Minkov, Qian Lin +3
Modulated optical cavities have been proposed and demonstrated for applications in communications, laser frequency stabilization, microwave-to-optical conversion and frequency comb…
On the Saturation Effect of Kernel Ridge Regression
Yicheng Li, Haobo Zhang, Qian Lin
The saturation effect refers to the phenomenon that the kernel ridge regression (KRR) fails to achieve the information theoretical lower bound when the smoothness of the undergroun…
Signed Support Recovery for Single Index Models in High-Dimensions
Matey Neykov, Qian Lin, Jun S. Liu
In this paper we study the support recovery problem for single index models , where is an unknown link function, $\bo…
Passive intrinsic-linewidth narrowing of ultraviolet extended-cavity diode laser by weak optical feedback
Polnop Samutpraphoot, Sophie Weber, Qian Lin +7
We present a simple method for narrowing the intrinsic Lorentzian linewidth of a commercial ultraviolet grating extended-cavity diode laser (TOPTICA DL Pro) using weak optical feed…
Dynamic indifference pricing via the G-expectation
Qian Lin
We study the dynamic indifference pricing with ambiguity preferences. For this, we introduce the dynamic expected utility with ambiguity via the nonlinear expectation--G-expectatio…
The Disruptions of 5G on Data-driven Technologies and Applications
Dumitrel Loghin, Shaofeng Cai, Gang Chen +12
With 5G on the verge of being adopted as the next mobile network, there is a need to analyze its impact on the landscape of computing and data management. In this paper, we analyze…
Improving Adaptivity via Over-Parameterization in Sequence Models
Yicheng Li, Qian Lin
It is well known that eigenfunctions of a kernel play a crucial role in kernel regression. Through several examples, we demonstrate that even with the same set of eigenfunctions, t…
The phase diagram of kernel interpolation in large dimensions
Haobo Zhang, Weihao Lu, Qian Lin
The generalization ability of kernel interpolation in large dimensions (i.e., for some ) might be one of the most interesting problems in the recent renaissan…
Print Defect Mapping with Semantic Segmentation
Augusto C. Valente, Cristina Wada, Deangela Neves +6
Efficient automated print defect mapping is valuable to the printing industry since such defects directly influence customer-perceived printer quality and manually mapping them is…
UStore: A Distributed Storage With Rich Semantics
Anh Dinh, Ji Wang, Sheng Wang +9
Today's storage systems expose abstractions which are either too low-level (e.g., key-value store, raw-block store) that they require developers to re-invent the wheels, or too hig…
Global testing under the sparse alternatives for single index models
Qian Lin, Zhigen Zhao, Jun S. Liu
For the single index model $y=f(β^Ïx,ε)$ with Gaussian design, %satisfying that rank where is unknown and is a sparse -dimensional unit…
On the Optimality of Functional Sliced Inverse Regression
Rui Chen, Songtao Tian, Dongming Huang +2
In this paper, we prove that functional sliced inverse regression (FSIR) achieves the optimal (minimax) rate for estimating the central space in functional sufficient dimension red…
Learning Curves and Benign Overfitting of Spectral Algorithms in Large Dimensions
Weihao Lu, Qian Lin, Yingcun Xia +1
Existing large-dimensional theory for spectral algorithms resolves either the optimally tuned point or the interpolation limit, but leaves the under-regularized regime unexplored.…
Large Dimensional Kernel Ridge Regression: Extending to Product Kernels
Yang Zhou, Yicheng Li, Yuqian Cheng +1
Recent studies have reported and in large dimensional kernel ridge regression (KRR). However, these findings are…
Blockchains vs. Distributed Databases: Dichotomy and Fusion
Pingcheng Ruan, Tien Tuan Anh Dinh, Dumitrel Loghin +4
Blockchain has come a long way: a system that was initially proposed specifically for cryptocurrencies is now being adapted and adopted as a general-purpose transactional system. A…
ForkBase: Immutable, Tamper-evident Storage Substrate for Branchable Applications
Qian Lin, Kaiyuan Yang, Tien Tuan Anh Dinh +8
Data collaboration activities typically require systematic or protocol-based coordination to be scalable. Git, an effective enabler for collaborative coding, has been attested for…
Nash equilibrium payoffs for stochastic differential games with reflection
Qian Lin
In this paper, we investigate Nash equilibrium payoffs for nonzero-sum stochastic differential games with reflection. We obtain an existence theorem and a characterization theorem…
Otem&Utem: Over- and Under-Translation Evaluation Metric for NMT
Jing Yang, Biao Zhang, Yue Qin +3
Although neural machine translation(NMT) yields promising translation performance, it unfortunately suffers from over- and under-translation is- sues [Tu et al., 2016], of which st…
Sparse Sliced Inverse Regression Via Lasso
Qian Lin, Zhigen Zhao, Jun S. Liu
For multiple index models, it has recently been shown that the sliced inverse regression (SIR) is consistent for estimating the sufficient dimension reduction (SDR) space if and on…
Nash equilibrium payoffs for stochastic differential games with jumps and coupled nonlinear cost functionals
Qian Lin
In this paper we investigate Nash equilibrium payoffs for two-player nonzero-sum stochastic differential games whose cost functionals are defined by a system of coupled backward st…
Reg3D: Reconstructive Geometry Instruction Tuning for 3D Scene Understanding
Hongpei Zheng, Lintao Xiang, Qijun Yang +2
The rapid development of Large Multimodal Models (LMMs) has led to remarkable progress in 2D visual understanding; however, extending these capabilities to 3D scene understanding r…
Multi-View Matching Network for 6D Pose Estimation
Daniel Mas Montserrat, Jianhang Chen, Qian Lin +2
Applications that interact with the real world such as augmented reality or robot manipulation require a good understanding of the location and pose of the surrounding objects. In…
SMORES-EP, a Modular Robot with Parallel Self-assembly
Chao Liu, Qian Lin, Hyun Kim +1
Self-assembly of modular robotic systems enables the construction of complex robotic configurations to adapt to different tasks. This paper presents a framework for SMORES types of…
Supporting Evidence for the Adaptive Feature Program across Diverse Models
Yicheng Li, Qian Lin
Theoretically exploring the advantages of neural networks might be one of the most challenging problems in the AI era. An adaptive feature program has recently been proposed to ana…
Safe Offline Reinforcement Learning with Real-Time Budget Constraints
Qian Lin, Bo Tang, Zifan Wu +5
Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years. However, most existing works i…
On the Optimality of Misspecified Spectral Algorithms
Haobo Zhang, Yicheng Li, Qian Lin
In the misspecified spectral algorithms problem, researchers usually assume the underground true function , a less-smooth interpolation space of a r…
Kernel interpolation generalizes poorly
Yicheng Li, Haobo Zhang, Qian Lin
One of the most interesting problems in the recent renaissance of the studies in kernel regression might be whether the kernel interpolation can generalize well, since it may help…
CRIMP: Compact & Reliable DNN Inference on In-Memory Processing via Crossbar-Aligned Compression and Non-ideality Adaptation
Shuo Huai, Hao Kong, Xiangzhong Luo +5
Crossbar-based In-Memory Processing (IMP) accelerators achieve high-speed, low-power computing for deep neural networks (DNNs), but face three obstacles. First, floating-point (FP)…
Local time and Tanaka formula for G-Brownian Motion
Qian Lin
In this paper, we study the notion of local time and Tanaka formula for the G-Brownian motion. Moreover, the joint continuity of the local time of the G-Brownian motion is obtained…
On the optimality of sliced inverse regression in high dimensions
Qian Lin, Xinran Li, Dongming Huang +1
The central subspace of a pair of random variables is the minimal subspace such that …
Erbium doped yttrium oxide thin films grown by chemical vapour deposition for quantum technologies
Anna Blin, Alexander Kolar, Andrew Kamen +8
The obtention of quantum-grade rare-earth doped oxide thin films that can be integrated with optical cavities and microwave resonators is of great interest for the development of s…
LoCEC: Local Community-based Edge Classification in Large Online Social Networks
Chonggang Song, Qian Lin, Guohui Ling +4
Relationships in online social networks often imply social connections in the real world. An accurate understanding of relationship types benefits many applications, e.g. social ad…
Towards Scaling Blockchain Systems via Sharding
Hung Dang, Tien Tuan Anh Dinh, Dumitrel Loghin +3
Existing blockchain systems scale poorly because of their distributed consensus protocols. Current attempts at improving blockchain scalability are limited to cryptocurrency. Scali…
A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues
Qian Lin, Hwee Tou Ng
Identifying breakdowns in ongoing dialogues helps to improve communication effectiveness. Most prior work on this topic relies on human annotated data and data augmentation to lear…
Horizon-unbiased Investment with Ambiguity
Qian Lin, Xianming Sun, Chao Zhou
In the presence of ambiguity on the driving force of market randomness, we consider the dynamic portfolio choice without any predetermined investment horizon. The investment criter…
Highest weight modules at the critical level and noncommutative Springer resolution
Roman Bezrukavnikov, Qian Lin
In arXiv:1001.2562 a certain non-commutative algebra was defined starting from a semi-simple algebraic group, so that the derived category of -modules is equivalent to the d…
Policy-regularized Offline Multi-objective Reinforcement Learning
Qian Lin, Chao Yu, Zongkai Liu +1
In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach f…
Synthetic Dimension in Photonics
Luqi Yuan, Qian Lin, Meng Xiao +1
The physics of a photonic structure is commonly described in terms of its apparent geometric dimensionality. On the other hand, with the concept of synthetic dimension, it is in fa…
Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks
Biao Zhang, Deyi Xiong, Jinsong Su +2
In this paper, we propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation. The recurrent units of ATR are heavily simplified to hav…
Off-Policy Primal-Dual Safe Reinforcement Learning
Zifan Wu, Bo Tang, Qian Lin +5
Primal-dual safe RL methods commonly perform iterations between the primal update of the policy and the dual update of the Lagrange Multiplier. Such a training paradigm is highly s…
Isogeny orbits in a family of abelian varieties
Qian Lin, Ming-Xi Wang
We prove that if a curve of a non-isotrivial family of abelian varieties over a curve contains infinitely many isogeny orbits of a finitely generated subgroup of a simple abelian v…
Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
Hao Kong, Di Liu, Xiangzhong Luo +5
The paper introduces TECO, a framework that jointly prunes depth, width, and input resolution of convolutional neural networks to improve speed and resource usage on embedded devic…
Constructing three-dimensional photonic topological insulator using two-dimensional ring resonator lattice with a synthetic frequency dimension
Qian Lin, Xiao-Qi Sun, Meng Xiao +2
In the development of topological photonics, achieving three dimensional topological insulators is of significant interest since it enables the exploration of new topological physi…
Experimental band structure spectroscopy along a synthetic dimension
Avik Dutt, Momchil Minkov, Qian Lin +3
In recent years there has been significant interest in the concepts of synthetic dimensions, where one couples the internal degrees of freedom of a particle to form higher-dimensio…
Properties of solutions of stochastic differential equations driven by the G-Brownian motion
Qian Lin
In this paper, we study the differentiability of solutions of stochastic differential equations driven by the -Brownian motion with respect to the initial data and the parameter…
An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
Qian Lin, Zongkai Liu, Danying Mo +1
In recent years, significant progress has been made in multi-objective reinforcement learning (RL) research, which aims to balance multiple objectives by incorporating preferences…
A single photonic cavity with two independent physical synthetic dimensions
Avik Dutt, Qian Lin, Luqi Yuan +3
The concept of synthetic dimensions, which has enabled the study of higher-dimensional physics on lower-dimensional physical structures, has generated significant recent interest i…
The Tychonoff uniqueness theorem for the G-heat equation
Qian Lin
In this paper, we obtain the Tychonoff uniqueness theorem for the G-heat equation.
On the Optimality of Misspecified Kernel Ridge Regression
Haobo Zhang, Yicheng Li, Weihao Lu +1
In the misspecified kernel ridge regression problem, researchers usually assume the underground true function , a less-smooth interpolation space of…
Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution
Xiaoyu Xiang, Qian Lin, Jan P. Allebach
Due to the limits of bandwidth and storage space, digital images are usually down-scaled and compressed when transmitted over networks, resulting in loss of details and jarring art…
Optimal control of coupled forward-backward stochastic system with jumps and related Hamilton-Jacobi-Bellman equations
Qian Lin
In this paper we investigate a kind of optimal control problem of coupled forward-backward stochastic system with jumps whose cost functional is defined through a coupled forward-b…
ForkBase: An Efficient Storage Engine for Blockchain and Forkable Applications
Sheng Wang, Tien Tuan Anh Dinh, Qian Lin +7
Existing data storage systems offer a wide range of functionalities to accommodate an equally diverse range of applications. However, new classes of applications have emerged, e.g.…
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
Ali Larian, Qian Lin, Chang Zong Wu +1
As autonomous agents are increasingly deployed across diverse operational contexts, aligning their behavior with human intent demands reward functions that remain robust to such ch…
Optimal Confidence Band for Kernel Gradient Flow Estimator
Yuqian Cheng, Zhuo Chen, Qian Lin
In this paper, we investigate the supremum-norm generalization error and the uniform inference for a specific class of kernel regression methods, namely the kernel gradient flows.…
Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels
Dongming Huang, Zhifan Li, Yicheng Li +1
We study spectral algorithms in the setting where kernels are learned from data. We introduce the effective span dimension (ESD), an alignment-sensitive complexity measure that dep…
MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines
Zhaojing Luo, Sai Ho Yeung, Meihui Zhang +7
With the ever-increasing adoption of machine learning for data analytics, maintaining a machine learning pipeline is becoming more complex as both the datasets and trained models e…
Overload Control for Scaling WeChat Microservices
Hao Zhou, Ming Chen, Qian Lin +6
Effective overload control for large-scale online service system is crucial for protecting the system backend from overload. Conventionally, the design of overload control is ad-ho…
EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems
Shuo Huai, Hao Kong, Shiqing Li +5
Edge devices are increasingly utilized for deploying deep learning applications on embedded systems. The real-time nature of many applications and the limited resources of edge dev…
The Optimality of Kernel Classifiers in Sobolev Space
Jianfa Lai, Zhifan Li, Dongming Huang +1
Kernel methods are widely used in machine learning, especially for classification problems. However, the theoretical analysis of kernel classification is still limited. This paper…