• Publications
  • Influence
An improved harmony search algorithm for solving optimization problems
TLDR
The impacts of constant parameters on harmony search algorithm are discussed and a strategy for tuning these parameters is presented and the proposed algorithm can find better solutions when compared to HS and other heuristic or deterministic methods. Expand
Global-best harmony search
TLDR
A new variant of HS, called global-best harmony search (GHS), is proposed in this paper where concepts from swarm intelligence are borrowed to enhance the performance of HS. Expand
Trading regret for efficiency: online convex optimization with long term constraints
TLDR
This paper proposes an efficient algorithm which achieves O(√T) regret bound and O(T3/4) bound on the violation of constraints and proposes a multipoint bandit feedback algorithm with the same bounds in expectation as the first algorithm. Expand
Online Optimization with Gradual Variations
TLDR
It is shown that for the linear and general smooth convex loss functions, an online algorithm modified from the gradient descend algorithm can achieve a regret which only scales as the square root of the deviation, and as an application, this can also have such a logarithmic regret for the portfolio management problem. Expand
Nyström Method vs Random Fourier Features: A Theoretical and Empirical Comparison
TLDR
It is shown that when there is a large gap in the eigen-spectrum of the kernel matrix, approaches based on the Nystrom method can yield impressively better generalization error bound than random Fourier features based approach. Expand
Linear Convergence with Condition Number Independent Access of Full Gradients
TLDR
This paper proposes to remove the dependence on the condition number by allowing the algorithm to access stochastic gradients of the objective function, and presents a novel algorithm named Epoch Mixed Gradient Descent (EMGD) that is able to utilize two kinds of gradients. Expand
Matrix Factorization with Explicit Trust and Distrust Side Information for Improved Social Recommendation
TLDR
A matrix factorization-based model for recommendation in social rating networks that properly incorporates both trust and distrust relationships aiming to improve the quality of recommendations and mitigate the data sparsity and cold-start users issues is proposed. Expand
Hybridizing harmony search algorithm with sequential quadratic programming for engineering optimization problems
This study presents a hybrid harmony search algorithm (HHSA) to solve engineering optimization problems with continuous design variables. Although the harmony search algorithm (HSA) has proven itsExpand
Robust Ensemble Clustering by Matrix Completion
TLDR
The proposed algorithm constructs a partially observed similarity matrix based on the data pairs whose cluster memberships are agreed upon by most of the clustering algorithms in the ensemble, and deploys the matrix completion algorithm to complete the similarity matrix. Expand
Adaptive Personalized Federated Learning
TLDR
Information theoretically, it is proved that the mixture of local and global models can reduce the generalization error and a communication-reduced bilevel optimization method is proposed, which reduces the communication rounds to $O(\sqrt{T})$ and can achieve a convergence rate of $O(1/T)$ with some residual error. Expand
...
1
2
3
4
5
...