Search Results for author:
Found 13 papers, 3 papers with code
M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling
We address the online combinatorial choice of weight multipliers for multi-objective optimization of many loss terms parameterized by neural works via a probabilistic graphical model (PGM) for the joint model parameter and multiplier evolution process, with a hypervolume based likelihood promoting multi-objective descent.
Almost Exact Recovery in Gossip Opinion Dynamics over Stochastic Block Models
It is shown that, when the influence of stubborn agents is small and the link probability within communities is large, an algorithm based on clustering transient agent states can achieve almost exact recovery of the communities.
Data-Driven Kalman Filter using Maximum Likelihood Optimization
A novel data-driven Kalman filter (DDKF) that combines model identification with state estimation is developed using pre-collected input-output data and uncertain initial state information of the unknown system.
Joint Learning of Network Topology and Opinion Dynamics Based on Bandit Algorithms
We study joint learning of network topology and a mixed opinion dynamics, in which agents may have different update rules.
What is the Expected Transient Behavior of Opinion Evolution for Two Communities?
Moreover, it is shown that the expected states of the agents in the same community concentrate around the initial average opinion of that community, if the weights within communities are larger than between.
Concentration in Gossip Opinion Dynamics over Random Graphs
Leveraging matrix perturbation results, we show how such concentration can help study the effect of network structure on the expected final opinions in two cases: (i) When the influence of stubborn agents is large, the expected final opinions polarize and are close to stubborn agents' opinions.
On the Convergence of mSGD and AdaGrad for Stochastic Optimization
First, we prove that the iterates of mSGD are asymptotically convergent to a connected set of stationary points with probability one, which is more general than existing works on subsequence convergence or convergence of time averages.
Identification of Linear Systems with Multiplicative Noise from Multiple Trajectory Data
An algorithm based on the least-squares method and multiple-trajectory data is proposed for joint estimation of the nominal system matrices and the covariance matrix of the multiplicative noise.
Event-Triggered Distributed Estimation With Decaying Communication Rate
We show that given the step size, adjusting the decay speed of the triggering threshold can lead to a tradeoff between the convergence rate of the estimation error and the decay speed of the communication rate.
Community Structure Recovery and Interaction Probability Estimation for Gossip Opinion Dynamics
The considered problem is to jointly recover the community labels of the agents and estimate interaction probabilities between the agents, based on a single trajectory of the model.
Linear System Identification Under Multiplicative Noise from Multiple Trajectory Data
The study of multiplicative noise models has a long history in control theory but is re-emerging in the context of complex networked systems and systems with learning-based control.
A Novel User Representation Paradigm for Making Personalized Candidate Retrieval
Our work is undergoing a anonymous review, and it will soon be released after the notification.
DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN Accelerators
On the Xilinx ZU2 @330 MHz and ZU9 @330 MHz, we achieve equivalently state-of-the-art performance on our benchmarks by na\"ive implementations without optimizations, and the throughput is further improved up to 1. 26x by leveraging heterogeneous optimizations in DNNVM.
