Suchergebnisse - "data-driven algorithm design"

Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization von Balcan, Maria-Florina, Dick, Travis, Vitercik, Ellen

“… A crucial problem in modern data science is data-driven algorithm design, where the goal is to choose the best algorithm, or algorithm parameters, for a specific application domain …”
Volltext

Data-driven Algorithm Design von Maria-Florina Balcan

“… Data driven algorithm design is an important aspect of modern data science and algorithm design …”
Volltext

Learn to optimize—a brief overview von Tang, Ke, Yao, Xin

“… Most optimization problems of practical significance are typically solved by highly configurable parameterized algorithms. To achieve the best performance on a …”
Volltext

Accelerating ERM for data-driven algorithm design using output-sensitive techniques von Maria-Florina Balcan, Seiler, Christopher, Sharma, Dravyansh

“… Data-driven algorithm design is a promising, learning-based approach for beyond worst-case analysis of algorithms with tunable parameters …”
Volltext

How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design von Maria-Florina Balcan, DeBlasio, Dan, Dick, Travis, Kingsford, Carl, Sandholm, Tuomas, Vitercik, Ellen

“… Worst-case instances, however, may be rare or nonexistent in practice. A growing body of research has demonstrated that data-driven algorithm design can lead to significant improvements in performance …”
Volltext

Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization von Maria-Florina Balcan, Dick, Travis, Vitercik, Ellen

“… Data-driven algorithm design, that is, choosing the best algorithm for a specific application, is a crucial problem in modern data science …”
Volltext

Adaptivity, Structure, and Objectives in Sequential Decision-Making von Sinclair, Sean R

“… Sequential decision-making algorithms are ubiquitous in the design and optimization of large-scale systems due to their practical impact, leading to a …”
Volltext

Algorithm Configuration for Structured Pfaffian Settings von Maria-Florina Balcan, Anh Tuan Nguyen, Sharma, Dravyansh

“… Data-driven algorithm design automatically adapts algorithms to specific application domains, achieving better performance …”
Volltext

Learning-Based Search Algorithm Design von Chen, Binghong

“… Classical search algorithms, such as A* search, evolutionary search, and Monte Carlo tree search, play a central role in solving many combinatorial …”
Volltext

Contributions to Data-Driven Combinatorial Solvers von Vaezipoor, Pashootan

“… Data-driven algorithm design provides a potential solution to this dilemma by tuning various aspects of the solver via machine learning to the desired distribution of a particular domain …”
Volltext

Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut von Cheng, Hongyu, Khalife, Sammy, Fiedorowicz, Barbara, Basu, Amitabh

“… Data-driven algorithm design is a paradigm that uses statistical and machine learning techniques to select from a class of algorithms for a computational problem an algorithm that has the …”
Volltext

Semi-bandit Optimization in the Dispersed Setting von Maria-Florina Balcan, Dick, Travis, Pegden, Wesley

“… The goal of data-driven algorithm design is to obtain high-performing algorithms for specific application domains using machine learning and data …”
Volltext

New Guarantees for Learning Revenue Maximizing Menus of Lotteries and Two-Part Tariffs von Maria-Florina Balcan, Beyhaghi, Hedyeh

“… We advance a recently flourishing line of work at the intersection of learning theory and computational economics by studying the learnability of two classes …”
Volltext

Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming von Sakaue, Shinsaku, Oki, Taihei

“… How to solve high-dimensional linear programs (LPs) efficiently is a fundamental question. Recently, there has been a surge of interest in reducing LP sizes …”
Volltext

Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A Search von Sakaue, Shinsaku, Oki, Taihei

“… and A*. We build on a recent framework called \textit{data-driven algorithm design} and evaluate the \textit{pseudo-dimension} of a class of utility functions that measure the performance of parameterized algorithms …”
Volltext

Learning-to-learn non-convex piecewise-Lipschitz functions von Maria-Florina Balcan, Khodak, Mikhail, Sharma, Dravyansh, Talwalkar, Ameet

“… We analyze the meta-learning of the initialization and step-size of learning algorithms for piecewise-Lipschitz functions, a non-convex setting with …”
Volltext

A General Large Neighborhood Search Framework for Solving Integer Linear Programs von Song, Jialin, Lanka, Ravi, Yue, Yisong, Dilkina, Bistra

“… This paper studies a strategy for data-driven algorithm design for large-scale combinatorial optimization problems that can leverage existing state-of-the-art solvers in general purpose ways …”
Volltext