Search Results for author: Alina Ene

Found 18 papers, 1 papers with code

Online and Streaming Algorithms for Constrained $k$-Submodular Maximization

no code implementations25 May 2023 Fabian Spaeh, Alina Ene, Huy L. Nguyen

Constrained $k$-submodular maximization is a general framework that captures many discrete optimization problems such as ad allocation, influence maximization, personalized recommendation, and many others.

High Probability Convergence of Stochastic Gradient Methods

no code implementations28 Feb 2023 Zijian Liu, Ta Duy Nguyen, Thien Hang Nguyen, Alina Ene, Huy Lê Nguyen

Instead, we show high probability convergence with bounds depending on the initial distance to the optimal solution.

Vocal Bursts Intensity Prediction

High Probability Convergence for Accelerated Stochastic Mirror Descent

no code implementations3 Oct 2022 Alina Ene, Huy L. Nguyen

In this work, we describe a generic approach to show convergence with high probability for stochastic convex optimization.

Vocal Bursts Intensity Prediction

META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions

no code implementations29 Sep 2022 Zijian Liu, Ta Duy Nguyen, Thien Hang Nguyen, Alina Ene, Huy L. Nguyen

There, STORM utilizes recursive momentum to achieve the VR effect and is then later made fully adaptive in STORM+ [Levy et al., '21], where full-adaptivity removes the requirement for obtaining certain problem-specific parameters such as the smoothness of the objective and bounds on the variance and norm of the stochastic gradients in order to set the step size.

Stochastic Optimization

On the Convergence of AdaGrad(Norm) on $\R^{d}$: Beyond Convexity, Non-Asymptotic Rate and Acceleration

no code implementations29 Sep 2022 Zijian Liu, Ta Duy Nguyen, Alina Ene, Huy L. Nguyen

Finally, we give new accelerated adaptive algorithms and their convergence guarantee in the deterministic setting with explicit dependency on the problem parameters, improving upon the asymptotic rate shown in previous works.

Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints

1 code implementation International Conference on Machine Learning 2022 Alina Ene, Huy L. Nguyen

Maximizing a monotone k-submodular function subject to cardinality constraints is a general model for several applications ranging from influence maximization with multiple products to sensor placement with multiple sensor types and online ad allocation.

POS

Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction

no code implementations28 Jan 2022 Zijian Liu, Ta Duy Nguyen, Alina Ene, Huy L. Nguyen

To address this problem, we propose two novel adaptive VR algorithms: Adaptive Variance Reduced Accelerated Extra-Gradient (AdaVRAE) and Adaptive Variance Reduced Accelerated Gradient (AdaVRAG).

Projection-Free Bandit Optimization with Privacy Guarantees

no code implementations22 Dec 2020 Alina Ene, Huy L. Nguyen, Adrian Vladu

We design differentially private algorithms for the bandit convex optimization problem in the projection-free setting.

Adaptive and Universal Algorithms for Variational Inequalities with Optimal Convergence

no code implementations15 Oct 2020 Alina Ene, Huy L. Nguyen

We show that our algorithms are universal and simultaneously achieve the optimal convergence rates in the non-smooth, smooth, and stochastic settings.

Parallel Algorithm for Non-Monotone DR-Submodular Maximization

no code implementations ICML 2020 Alina Ene, Huy L. Nguyen

For any desired accuracy $\epsilon$, our algorithm achieves a $1/e - \epsilon$ approximation using $O(\log{n} \log(1/\epsilon) / \epsilon^3)$ parallel rounds of function evaluations.

Improved Convergence for $\ell_\infty$ and $\ell_1$ Regression via Iteratively Reweighted Least Squares

no code implementations18 Feb 2019 Alina Ene, Adrian Vladu

The iteratively reweighted least squares method (IRLS) is a popular technique used in practice for solving regression problems.

Data Structures and Algorithms

A Parallel Double Greedy Algorithm for Submodular Maximization

no code implementations4 Dec 2018 Alina Ene, Huy L. Nguyen, Adrian Vladu

We study parallel algorithms for the problem of maximizing a non-negative submodular function.

Decomposable Submodular Function Minimization: Discrete and Continuous

no code implementations NeurIPS 2017 Alina Ene, Huy L. Nguyen, László A. Végh

This paper investigates connections between discrete and continuous approaches for decomposable submodular function minimization.

A Reduction for Optimizing Lattice Submodular Functions with Diminishing Returns

no code implementations27 Jun 2016 Alina Ene, Huy L. Nguyen

A function $f: \mathbb{Z}_+^E \rightarrow \mathbb{R}_+$ is DR-submodular if it satisfies $f({\bf x} + \chi_i) -f ({\bf x}) \ge f({\bf y} + \chi_i) - f({\bf y})$ for all ${\bf x}\le {\bf y}, i\in E$.

A New Framework for Distributed Submodular Maximization

no code implementations14 Jul 2015 Rafael da Ponte Barbosa, Alina Ene, Huy L. Nguyen, Justin Ward

A wide variety of problems in machine learning, including exemplar clustering, document summarization, and sensor placement, can be cast as constrained submodular maximization problems.

BIG-bench Machine Learning Clustering +1

Random Coordinate Descent Methods for Minimizing Decomposable Submodular Functions

no code implementations9 Feb 2015 Alina Ene, Huy L. Nguyen

Submodular function minimization is a fundamental optimization problem that arises in several applications in machine learning and computer vision.

BIG-bench Machine Learning

The Power of Randomization: Distributed Submodular Maximization on Massive Datasets

no code implementations9 Feb 2015 Rafael da Ponte Barbosa, Alina Ene, Huy L. Nguyen, Justin Ward

A wide variety of problems in machine learning, including exemplar clustering, document summarization, and sensor placement, can be cast as constrained submodular maximization problems.

BIG-bench Machine Learning Clustering +1

Cannot find the paper you are looking for? You can Submit a new open access paper.