相关论文: Towards Direct Evaluation of Harness Optimizers vi…

As the demand for computational power grows, optimizing code through compilers becomes increasingly crucial. In this context, we focus on fully automatic code optimization techniques that automate the process of selecting and applying code…

Aspects such as limited resources, frequently changing market demands, and different technical restrictions regarding the implementation of software requirements (features) often demand for the prioritization of requirements. The task of…

Recommender systems are expected to be assistants that help human users find relevant information automatically without explicit queries. As recommender systems evolve, increasingly sophisticated learning techniques are applied and have…

We investigate the problem of designing optimal classifiers in the strategic classification setting, where the classification is part of a game in which players can modify their features to attain a favorable classification outcome (while…

Due to the nonlinear nature of Deep Neural Networks (DNNs), one can not guarantee convergence to a unique global minimum of the loss when using optimizers relying only on local information, such as SGD. Indeed, this was a primary source of…

Evaluating the adversarial robustness of machine learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fast minimum-norm attacks by automating the selection of the…

Many optimizers have been proposed for training deep neural networks, and they often have multiple hyperparameters, which make it tricky to benchmark their performance. In this work, we propose a new benchmarking protocol to evaluate both…

A recent line of works apply machine learning techniques to assist or rebuild cost-based query optimizers in DBMS. While exhibiting superiority in some benchmarks, their deficiencies, e.g., unstable performance, high training cost, and slow…

Algorithms are used to aid human decision makers by making predictions and recommending decisions. Currently, these algorithms are trained to optimize prediction accuracy. What if they were optimized to control final decisions? In this…

This paper studies algorithmic decision-making under human's strategic behavior, where a decision maker uses an algorithm to make decisions about human agents, and the latter with information about the algorithm may exert effort…

Coordinating agents to complete a set of tasks with intercoupled temporal and resource constraints is computationally challenging, yet human domain experts can solve these difficult scheduling problems using paradigms learned through years…

Personalization plays an important role in many services, just as news does. Many studies have examined news personalization algorithms, but few have considered practical environments. This paper provides algorithms and system architecture…

There has been substantial progress in summarization research enabled by the availability of novel, often large-scale, datasets and recent advances on neural network-based approaches. However, manual evaluation of the system generated…

Choosing the optimizer is considered to be among the most crucial design decisions in deep learning, and it is not an easy one. The growing literature now lists hundreds of optimization methods. In the absence of clear theoretical guidance…

Metaheuristic algorithms are essential for solving complex optimization problems in different fields. However, the difficulty in comparing and rating these algorithms remains due to the wide range of performance metrics and problem…

Learned optimizers are increasingly effective, with performance exceeding that of hand designed optimizers such as Adam~\citep{kingma2014adam} on specific tasks \citep{metz2019understanding}. Despite the potential gains available, in…

Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted metrics or static/snapshot-based criteria to estimate…

Data bias, e.g., popularity impairs the dynamics of two-sided markets within recommender systems. This overshadows the less visible but potentially intriguing long-tail items that could capture user interest. Despite the abundance of…

Learning control policies to perform complex robotics tasks from human preference data presents significant challenges. On the one hand, the complexity of such tasks typically requires learning policies to perform a variety of subtasks,…

Many important multiple-objective decision problems can be cast within the framework of ranking under constraints and solved via a weighted bipartite matching linear program. Some of these optimization problems, such as personalized content…