Search Results for author:
Found 27 papers, 8 papers with code
Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection
Video moment retrieval and highlight detection are two highly valuable tasks in video understanding, but until recently they have been jointly studied.
E2USD: Efficient-yet-effective Unsupervised State Detection for Multivariate Time Series
We propose E2USD that enables efficient-yet-accurate unsupervised MTS state detection.
On the $O(\frac{\sqrt{d}}{T^{1/4}})$ Convergence Rate of RMSProp and Its Momentum Extension Measured by $\ell_1$ Norm
Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with respect to their dependence on the dimension.
Missing Value Imputation for Multi-attribute Sensor Data Streams via Message Propagation (Extended Version)
First, we propose a message propagation imputation network (MPIN) that is able to recover the missing values of data instances in a time window.
Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
This approach is characterized by a two-stage process: drafting and verification.
DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference
Due to limited resources on edge and different characteristics of deep neural network (DNN) models, it is a big challenge to optimize DNN inference performance in terms of energy consumption and end-to-end latency on edge devices.
BCEdge: SLO-Aware DNN Inference Services with Adaptive Batching on Edge Platforms
As deep neural networks (DNNs) are being applied to a wide range of edge intelligent applications, it is critical for edge inference platforms to have both high-throughput and low-latency at the same time.
LightCTS: A Lightweight Framework for Correlated Time Series Forecasting
Many deep learning models have been proposed to improve the accuracy of CTS forecasting.
Ranked #1 on
Traffic Prediction
on PeMS04
(FLOPs(M) metric, using extra
training data)
Computational Efficiency
Correlated Time Series Forecasting
+4
Inverse Compositional Learning for Weakly-supervised Relation Grounding
In this study, we introduce a novel approach called inverse compositional learning (ICL) for weakly-supervised video relation grounding.
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
Adan first reformulates the vanilla Nesterov acceleration to develop a new Nesterov momentum estimation (NME) method, which avoids the extra overhead of computing gradient at the extrapolation point.
Sublinear Algorithms for Hierarchical Clustering
At the heart of our algorithmic results is a view of the objective in terms of cuts in the graph, which allows us to use a relaxed notion of cut sparsifiers to do hierarchical clustering while introducing only a small distortion in the objective function.
Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(ε^{-7/4})$ Complexity
They do not invoke negative curvature exploitation or minimization of regularized surrogate functions as the subroutines.
Approximate optimization of convex functions with outlier noise
We study the problem of minimizing a convex function given by a zeroth order oracle that is possibly corrupted by {\em outlier noise}.
Accelerated Gradient Tracking over Time-varying Graphs for Decentralized Optimization
We prove the $O((\frac{\gamma}{1-\sigma_{\gamma}})^2\sqrt{\frac{L}{\epsilon}})$ and $O((\frac{\gamma}{1-\sigma_{\gamma}})^{1. 5}\sqrt{\frac{L}{\mu}}\log\frac{1}{\epsilon})$ complexities for the practical single loop accelerated gradient tracking over time-varying graphs when the problems are nonstrongly convex and strongly convex, respectively, where $\gamma$ and $\sigma_{\gamma}$ are two common constants charactering the network connectivity, $\epsilon$ is the desired precision, and $L$ and $\mu$ are the smoothness and strong convexity constants, respectively.
An Experimental Analysis of Indoor Spatial Queries: Modeling, Indexing, and Processing
Indoor location-based services (LBS), such as POI search and routing, are often built on top of typical indoor spatial queries.
Databases Data Structures and Algorithms
Variance Reduced EXTRA and DIGing and Their Optimal Acceleration for Strongly Convex Decentralized Optimization
Our stochastic gradient computation complexities are the same as the ones of single-machine VR methods, such as SAG, SAGA, and SVRG, and our communication complexities keep the same as those of EXTRA and DIGing, respectively.
AIBench Training: Balanced Industry-Standard AI Training Benchmarking
We use real-world benchmarks to cover the factors space that impacts the learning dynamics to the most considerable extent.
Revisiting EXTRA for Smooth Distributed Optimization
EXTRA is a popular method for dencentralized distributed optimization and has broad applications.
AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite
An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application.
AIBench: An Industry Standard Internet Service AI Benchmark Suite
On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales.
Hermitian matrices for clustering directed graphs: insights and applications
Graph clustering is a basic technique in machine learning, and has widespread applications in different domains.
Optimization Algorithm Inspired Deep Neural Network Structure Design
In this paper, we propose the hypothesis that the neural network structure design can be inspired by optimization algorithms and a faster optimization algorithm may lead to a better neural network structure.
Strategies for Searching Video Content with Text Queries or Video Examples
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.
Accelerated Proximal Gradient Methods for Nonconvex Programming
However, it is still unknown whether the usual APG can ensure the convergence to a critical point in nonconvex programming.
Fast Proximal Linearized Alternating Direction Method of Multiplier with Parallel Splitting
The Augmented Lagragian Method (ALM) and Alternating Direction Method of Multiplier (ADMM) have been powerful optimization methods for general convex programming subject to linear constraint.
Optimized Projections for Compressed Sensing via Direct Mutual Coherence Minimization
To the best of our knowledge, this is the first work which directly minimizes the mutual coherence of the projected dictionary with a convergence guarantee.
Linearized Alternating Direction Method with Parallel Splitting and Adaptive Penalty for Separable Convex Programs in Machine Learning
However, the traditional alternating direction method (ADM) and its linearized version (LADM, obtained by linearizing the quadratic penalty term) are for the two-block case and cannot be naively generalized to solve the multi-block case.
