Search Results for author:
Found 19 papers, 4 papers with code
Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework
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.
GraphPub: Generation of Differential Privacy Graph with High Availability
In recent years, with the rapid development of graph neural networks (GNN), more and more graph datasets have been published for GNN tasks.
Interpretable Geoscience Artificial Intelligence (XGeoS-AI): Application to Demystify Image Recognition
Experimental results demonstrate that the effectiveness, versatility, and heuristics of the proposed framework have great potential in solving geoscience image recognition problems.
Uncertainty-aware Traffic Prediction under Missing Data
However, most studies assume the prediction locations have complete or at least partial historical records and cannot be extended to non-historical recorded locations.
Linear convergence of forward-backward accelerated algorithms without knowledge of the modulus of strong convexity
A significant milestone in modern gradient-based optimization was achieved with the development of Nesterov's accelerated gradient descent (NAG) method.
On Underdamped Nesterov's Acceleration
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.
Reinforcement Learning Approaches for Traffic Signal Control under Missing Data
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.
Linear Convergence of ISTA and FISTA
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.
Revisiting the acceleration phenomenon via high-resolution differential equations
Furthermore, we also investigate NAG from the implicit-velocity scheme.
LibSignal: An Open Library for Traffic Signal Control
This paper introduces a library for cross-simulator comparison of reinforcement learning models in traffic signal control tasks.
Proximal Subgradient Norm Minimization of ISTA and FISTA
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.
Gradient Norm Minimization of Nesterov Acceleration: $o(1/k^3)$
In the history of first-order algorithms, Nesterov's accelerated gradient descent (NAG) is one of the milestones.
Modeling Network-level Traffic Flow Transitions on Sparse Data
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.
An adjoint-free algorithm for conditional nonlinear optimal perturbations (CNOPs) via sampling
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.
On the Hyperparameters in Stochastic Gradient Descent with Momentum
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.
On Learning Rates and Schrödinger Operators
In this paper, we present a general theoretical analysis of the effect of the learning rate in stochastic gradient descent (SGD).
Acceleration via Symplectic Discretization of High-Resolution Differential Equations
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.
Understanding the Acceleration Phenomenon via High-Resolution Differential Equations
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.
A Conservation Law Method in Optimization
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.
