56 datasets found

The (cid:96)1 ball constrained optimization problem.

The dataset used in the paper is the copying memory task, which consists in remembering a sequence of letters from some alphabet A = {ak}N k=1.

Representing some problems with XOR clauses (parity constraints) can allow to apply more efficient reasoning techniques.

The dataset used in this paper is a simulation dataset for retinal prosthetic stimulation optimization. It contains 10,000,000 random stimulus-percept pairs and is used to...

The dataset used in the paper is a ridge regression problem (Millionsong) and a support vector machine (RCV1) and a matrix completion problem (Netflix) on a large-scale...

The dataset used in this paper is not explicitly described. However, it is mentioned that the authors used a Bayesian Optimization algorithm and a dataset for industrial process...

The dataset used in the paper is a simple test function with a discontinuity at x1 = c, x2 = 0.5. The function is unimodal if b = 0, bimodal if b > 0, and has a discontinuity...

The NL4Opt Generation Dataset consists of 1101 examples, divided into the train, dev, and test splits composed of 713, 99, and 289 examples, respectively. Each example consists...

The dataset used in the paper is a collection of 30 test functions with 30 and 50 dimensions, used for evaluating the performance of the Adaptive Coordinate System (ACoS)...

The dataset used in the paper is a stateful performative setting, where the data distribution reacts to the deployed model. The goal is to learn a model that both induces a...

Railway Operation Rescheduling System via Dynamic Simulation and Reinforcement Learning

The dataset used in the paper is a synthetic dataset for ridge regression problem over a network of agents, modeled as a Erdos-Renyi graph with m = 30 nodes and edge probability...

The dataset used in the paper is the LeadingOnes problem, a maximization problem where the goal is to find the maximum number of leading ones in a binary string.

DaCeML is a Data-Centric Machine Learning framework that provides a simple, flexible, and customizable pipeline for optimizing training of arbitrary deep neural networks.

The Beale function is a widely used optimization problem that has a single saddle point at (0, 1).

The dataset used in the paper is a 3-d Gaussian distributed dataset.

The dataset used in the paper is a synthetic dataset generated by the component decoupled model described in Section 3.

This dataset is used to test the robustness of watermarking methods against adaptive attacks.

The authors propose two algorithms for optimizing for the future in non-stationary MDPs.

The dataset used in the paper is not explicitly described, but it is mentioned that it is a class of regression models GN.