Climate change is one of the greatest challenges facing humanity, and we, as machine
learning (ML) experts, may wonder how we can help. Here we describe how ML can be a …

Stochastic algorithms are among the best methods for solving computationally hard search
and reasoning problems. The run time of such procedures can vary significantly from …

Citizen-science projects engage volunteers to gather or process data to address scientific
questions. But citizen-science projects vary in their ability to contribute usefully for science, …

Batch normalization (BN) is a technique to normalize activations in intermediate layers of
deep neural networks. Its tendency to improve accuracy and speed up training have …

… However, our experiments in Gomes (1998a) also suggest a heavy tail phenomenon on the
left-… Based on our data (Gomes 1998a), we conjecture that α for the tail on the left is less than …

Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment
and accelerate research, helping scientists to generate hypotheses, design experiments, …

There has been significant recent progress in reasoning and constraint processing methods.
In areas such as planning and finite model-checking, current solution techniques can …

We study the runtime distributions of backtrack procedures for propositional satisfiability and
constraint satisfaction. Such procedures often exhibit a large variability in performance. Our …

Publisher Summary The past few years have seen enormous progress in the performance
of Boolean satisfiability (SAT) solvers. Despite the worst-case exponential run time of all …

… CARLA GOMES Cornell University THOMAS DIETTERICH Oregon State University
CHRISTOPHER BARRETT Cornell University JON CONRAD Cornell University BISTRA DILKINA …