no code implementations • 17 Jan 2025 • Mingwei Fu, Bin Shi
In this paper, we introduce a family of controllable momentum coefficients for forward-backward accelerated methods, focusing on the critical step size $s=1/L$.
1 code implementation • 19 Dec 2024 • Yiming Xu, Bin Shi, Teng Ma, Bo Dong, Haoyi Zhou, Qinghua Zheng
The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation.
no code implementations • 18 Dec 2024 • Mingwei Fu, Bin Shi
The linear convergence derived from this Lyapunov function is independent of both the parameters of the strongly convex functions and the step size, yielding a more general and robust result.
1 code implementation • 17 Nov 2024 • Rui Zhao, Bin Shi, Zhiming Liang, Jianfei Ruan, Bo Dong, Lu Lin
This mitigates the impact of inaccurately labeled neighbors and diversifies the label set.
1 code implementation • CVPR 2024 • Rui Zhao, Bin Shi, Jianfei Ruan, Tianze Pan, Bo Dong
Utilizing this framework with part-level labels, we can learn the noisy class posteriors more precisely by guiding the model to integrate information from various parts, ultimately improving the classification performance.
no code implementations • 2 Mar 2024 • Junxian Li, Bin Shi, Erfei Cui, Hua Wei, Qinghua Zheng
To the best of our knowledge, it is the first work to include hidden layer distillation for student MLP on graphs and to combine graph Positional Encoding with MLP.
no code implementations • 28 Feb 2024 • Wanghan Xu, Bin Shi, Ao Liu, Jiqiang Zhang, Bo Dong
In recent years, with the rapid development of graph neural networks (GNN), more and more graph datasets have been published for GNN tasks.
no code implementations • 8 Nov 2023 • Jin-Jian Xu, Hao Zhang, Chao-Sheng Tang, Lin Li, Bin Shi
Experimental results demonstrate that the effectiveness, versatility, and heuristics of the proposed framework have great potential in solving geoscience image recognition problems.
1 code implementation • 13 Sep 2023 • Hao Mei, Junxian Li, Zhiming Liang, Guanjie Zheng, Bin Shi, Hua Wei
However, most studies assume the prediction locations have complete or at least partial historical records and cannot be extended to non-historical recorded locations.
no code implementations • 16 Jun 2023 • Bowen Li, Bin Shi, Ya-xiang Yuan
A significant milestone in modern gradient-based optimization was achieved with the development of Nesterov's accelerated gradient descent (NAG) method.
no code implementations • 28 Apr 2023 • Shuo Chen, Bin Shi, Ya-xiang Yuan
In this paper, based on the high-resolution differential equation framework, we construct the new Lyapunov functions for the underdamped case, which is motivated by the power of the time $t^{\gamma}$ or the iteration $k^{\gamma}$ in the mixed term.
1 code implementation • 21 Apr 2023 • Hao Mei, Junxian Li, Bin Shi, Hua Wei
In this work, we aim to control the traffic signals in a real-world setting, where some of the intersections in the road network are not installed with sensors and thus with no direct observations around them.
no code implementations • 13 Dec 2022 • Bowen Li, Bin Shi, Ya-xiang Yuan
Specifically, assuming the smooth part to be strongly convex is more reasonable for the least-square model, even though the image matrix is probably ill-conditioned.
no code implementations • 12 Dec 2022 • Shuo Chen, Bin Shi, Ya-xiang Yuan
Furthermore, we also investigate NAG from the implicit-velocity scheme.
2 code implementations • 19 Nov 2022 • Hao Mei, Xiaoliang Lei, Longchao Da, Bin Shi, Hua Wei
This paper introduces a library for cross-simulator comparison of reinforcement learning models in traffic signal control tasks.
no code implementations • 3 Nov 2022 • Bowen Li, Bin Shi, Ya-xiang Yuan
We apply the tighter inequality discovered in the well-constructed Lyapunov function and then obtain the proximal subgradient norm minimization by the phase-space representation, regardless of gradient-correction or implicit-velocity.
no code implementations • 19 Sep 2022 • Shuo Chen, Bin Shi, Ya-xiang Yuan
In the history of first-order algorithms, Nesterov's accelerated gradient descent (NAG) is one of the milestones.
1 code implementation • 13 Aug 2022 • Xiaoliang Lei, Hao Mei, Bin Shi, Hua Wei
DTIGNN models the traffic system as a dynamic graph influenced by traffic signals, learns the transition models grounded by fundamental transition equations from transportation, and predicts future traffic states with imputation in the process.
no code implementations • 1 Aug 2022 • Bin Shi, Guodong Sun
In this paper, we propose a sampling algorithm based on state-of-the-art statistical machine learning techniques to obtain conditional nonlinear optimal perturbations (CNOPs), which is different from traditional (deterministic) optimization methods. 1 Specifically, the traditional approach is unavailable in practice, which requires numerically computing the gradient (first-order information) such that the computation cost is expensive, since it needs a large number of times to run numerical models.
no code implementations • 9 Aug 2021 • Bin Shi
By comparison, we demonstrate how the optimal linear rate of convergence and the final gap for SGD only about the learning rate varies with the momentum coefficient increasing from zero to one when the momentum is introduced.
no code implementations • 15 Apr 2020 • Bin Shi, Weijie J. Su, Michael. I. Jordan
In this paper, we present a general theoretical analysis of the effect of the learning rate in stochastic gradient descent (SGD).
no code implementations • NeurIPS 2019 • Bin Shi, Simon S. Du, Weijie J. Su, Michael. I. Jordan
We study first-order optimization methods obtained by discretizing ordinary differential equations (ODEs) corresponding to Nesterov's accelerated gradient methods (NAGs) and Polyak's heavy-ball method.
no code implementations • 21 Oct 2018 • Bin Shi, Simon S. Du, Michael. I. Jordan, Weijie J. Su
We also show that these ODEs are more accurate surrogates for the underlying algorithms; in particular, they not only distinguish between NAG-SC and Polyak's heavy-ball method, but they allow the identification of a term that we refer to as "gradient correction" that is present in NAG-SC but not in the heavy-ball method and is responsible for the qualitative difference in convergence of the two methods.
no code implementations • 27 Aug 2017 • Bin Shi
We propose some algorithms to find local minima in nonconvex optimization and to obtain global minima in some degree from the Newton Second Law without friction.