no code implementations • 11 Feb 2024 • Jeongyeol Kwon, Dohyun Kwon, Hanbaek Lyu
We study the complexity of finding stationary points with such an $y^*$-aware oracle: we propose a simple first-order method that converges to an $\epsilon$ stationary point using $O(\epsilon^{-6}), O(\epsilon^{-4})$ access to first-order $y^*$-aware oracles.
1 code implementation • 15 Jan 2024 • William G. Powell, Hanbaek Lyu
For obtaining optimal first-order convergence guarantee for stochastic optimization, it is necessary to use a recurrent data sampling algorithm that samples every data point with sufficient frequency.
no code implementations • 16 Dec 2023 • Yuchen Li, Laura Balzano, Deanna Needell, Hanbaek Lyu
Block majorization-minimization (BMM) is a simple iterative algorithm for nonconvex optimization that sequentially minimizes a majorizing surrogate of the objective function in each block coordinate while the other block coordinates are held fixed.
1 code implementation • 16 Dec 2023 • Vishal Rana, Jianhao Peng, Chao Pan, Hanbaek Lyu, Albert Cheng, Minji Kim, Olgica Milenkovic
First, we demonstrate that online cvxNDL retains the accuracy of classical DL methods while simultaneously ensuring unique interpretability and scalability.
1 code implementation • 25 Nov 2023 • Agam Goyal, Zhaoxing Wu, Richard P. Yim, Binhao Chen, Zihong Xu, Hanbaek Lyu
A system of coupled oscillators on an arbitrary graph is locally driven by the tendency to mutual synchronization between nearby oscillators, but can and often exhibit nonlinear behavior on the whole graph.
1 code implementation • NeurIPS 2023 • Joowon Lee, Hanbaek Lyu, Weixin Yao
Supervised matrix factorization (SMF) is a classical machine learning method that simultaneously seeks feature extraction and classification tasks, which are not necessarily a priori aligned objectives.
no code implementations • 15 Nov 2023 • Keunsu Kim, Hanbaek Lyu, Jinsu Kim, Jae-Hun Jung
We propose a novel methodology for forecasting spatio-temporal data using supervised semi-nonnegative matrix factorization (SSNMF) with frequency regularization.
no code implementations • 4 Jun 2023 • Dohyun Kwon, Hanbaek Lyu
We consider the block coordinate descent methods of Gauss-Seidel type with proximal regularization (BCD-PR), which is a classical method of minimizing general nonconvex objectives under constraints that has a wide range of practical applications.
1 code implementation • 14 Jun 2022 • Joowon Lee, Hanbaek Lyu, Weixin Yao
Supervised dictionary learning (SDL) is a classical machine learning method that simultaneously seeks feature extraction and classification tasks, which are not necessarily a priori aligned objectives.
no code implementations • 29 Mar 2022 • Ahmet Alacaoglu, Hanbaek Lyu
As an application, we obtain first online nonnegative matrix factorization algorithms for dependent data based on stochastic projected gradient methods with adaptive step sizes and optimal rate of convergence.
1 code implementation • 5 Jan 2022 • Hanbaek Lyu
The surrogates are required to be strongly convex and convergence rate analysis for the general non-convex setting was not available.
2 code implementations • 13 Feb 2021 • Hanbaek Lyu, Yacoub H. Kureh, Joshua Vendrow, Mason A. Porter
It is common to use networks to encode the architecture of interactions between entities in complex systems in the physical, biological, social, and information sciences.
1 code implementation • 28 Dec 2020 • Hardeep Bassi, Richard Yim, Rohith Kodukula, Joshua Vendrow, Cherlin Zhu, Hanbaek Lyu
However, in the problem setting where these graph statistics cannot distinguish the two classes very well (e. g., when the graphs are generated from the same random graph model), we find that pairing a few iterations of the initial dynamics along with the graph statistics as the input to our classification algorithms can lead to significant improvement in accuracy; far exceeding what is known by the classical oscillator theory.
1 code implementation • 7 Dec 2020 • Hanbaek Lyu, Yuchen Li
Block majorization-minimization (BMM) is a simple iterative algorithm for nonconvex constrained optimization that sequentially minimizes majorizing surrogates of the objective function in each block coordinate while the other coordinates are held fixed.
no code implementations • 10 Nov 2020 • Hanbaek Lyu, Georg Menz, Deanna Needell, Christopher Strohmeier
Online nonnegative matrix factorization (ONMF) is a matrix factorization technique in the online setting where data are acquired in a streaming fashion and the matrix factors are updated each time.
1 code implementation • 4 Oct 2020 • Lara Kassab, Alona Kryshchenko, Hanbaek Lyu, Denali Molitor, Deanna Needell, Elizaveta Rebrova, Jiahong Yuan
Further, we propose quantitative ways to measure the topic length and demonstrate the ability of S-NCPD (as well as its online variant) to discover short and long-lasting temporal topics in a controlled manner in semi-synthetic and real-world data including news headlines.
1 code implementation • 16 Sep 2020 • Hanbaek Lyu, Christopher Strohmeier, Deanna Needell
We prove that our algorithm converges almost surely to the set of stationary points of the objective function under the hypothesis that the sequence of data tensors is generated by an underlying Markov chain.
2 code implementations • 20 Apr 2020 • Hanbaek Lyu, Christopher Strohmeier, Georg Menz, Deanna Needell
One of the main sources of difficulty is that a very limited amount of daily COVID-19 case data is available, and with few exceptions, the majority of countries are currently in the "exponential spread stage," and thus there is scarce information available which would enable one to predict the phase transition between spread and containment.
2 code implementations • 1 Dec 2019 • Yuchen Guo, Nicholas Hanoian, Zhexiao Lin, Nicholas Liskij, Hanbaek Lyu, Deanna Needell, Jiahao Qu, Henry Sojico, Yuliang Wang, Zhe Xiong, Zhenhong Zou
We propose a novel model for a topic-aware chatbot by combining the traditional Recurrent Neural Network (RNN) encoder-decoder model with a topic attention layer based on Nonnegative Matrix Factorization (NMF).
1 code implementation • 5 Nov 2019 • Hanbaek Lyu, Deanna Needell, Laura Balzano
As the main application, by combining online non-negative matrix factorization and a recent MCMC algorithm for sampling motifs from networks, we propose a novel framework of Network Dictionary Learning, which extracts ``network dictionary patches' from a given network in an online manner that encodes main features of the network.
2 code implementations • 21 Oct 2019 • Hanbaek Lyu, Facundo Memoli, David Sivakoff
We propose two complementary MCMC algorithms for sampling random graph homomorphisms and establish bounds on their mixing times and the concentration of their time averages.