Yannet Interian

Yannet Interian, Sara Bernardini

Local search algorithms are well-known methods for solving large, hard instances of the satisfiability problem (SAT). The performance of these algorithms crucially depends on heuristics for setting noise parameters and scoring variables. The optimal setting for these heuristics varies for different instance distributions. In this paper, we present an approach for learning effective variable scoring functions and noise parameters by using reinforcement learning. We consider satisfiability problems from different instance distributions and learn specialized heuristics for each of them. Our experimental results show improvements with respect to both a WalkSAT baseline and another local search learned heuristic.

Gilmer Valdes, Wilmer Arbelo, Yannet Interian et al.

Many regression and classification procedures fit a parameterized function $f(x;w)$ of predictor variables $x$ to data $\{x_{i},y_{i}\}_1^N$ based on some loss criterion $L(y,f)$. Often, regularization is applied to improve accuracy by placing a constraint $P(w)\leq t$ on the values of the parameters $w$. Although efficient methods exist for finding solutions to these constrained optimization problems for all values of $t\geq0$ in the special case when $f$ is a linear function, none are available when $f$ is non-linear (e.g. Neural Networks). Here we present a fast algorithm that provides all such solutions for any differentiable function $f$ and loss $L$, and any constraint $P$ that is an increasing monotone function of the absolute value of each parameter. Applications involving sparsity inducing regularization of arbitrary Neural Networks are discussed. Empirical results indicate that these sparse solutions are usually superior to their dense counterparts in both accuracy and interpretability. This improvement in accuracy can often make Neural Networks competitive with, and sometimes superior to, state-of-the-art methods in the analysis of tabular data.

Gilmer Valdes, Yannet Interian, Efstathios D. Gennatas Mark J. Van der Laan

In this article we consider the Conditional Super Learner (CSL), an algorithm which selects the best model candidate from a library conditional on the covariates. The CSL expands the idea of using cross-validation to select the best model and merges it with meta learning. Here we propose a specific algorithm that finds a local minimum to the problem posed, proof that it converges at a rate faster than $O_p(n^{-1/4})$ and offers extensive empirical evidence that it is an excellent candidate to substitute stacking or for the analysis of Hierarchical problems.

Khoury Ibrahim, Danielle A. Savage, Addie Schnirel et al.

Leveraging over 30,000 images each with up to 89 labels collected by Recology---an integrated resource recovery company with both residential and commercial trash, recycling and composting services---the authors develop ContamiNet, a convolutional neural network, to identify contaminating material in residential recycling and compost bins. When training the model on a subset of labels that meet a minimum frequency threshold, ContamiNet preforms almost as well human experts in detecting contamination (0.86 versus 0.88 AUC). Recology is actively piloting ContamiNet in their daily municipal solid waste (MSW) collection to identify contaminants in recycling and compost bins to subsequently inform and educate customers about best sorting practices.

E. D. Gennatas, J. H. Friedman, L. H. Ungar et al.

Machine Learning is proving invaluable across disciplines. However, its success is often limited by the quality and quantity of available data, while its adoption by the level of trust that models afford users. Human vs. machine performance is commonly compared empirically to decide whether a certain task should be performed by a computer or an expert. In reality, the optimal learning strategy may involve combining the complementary strengths of man and machine. Here we present Expert-Augmented Machine Learning (EAML), an automated method that guides the extraction of expert knowledge and its integration into machine-learned models. We use a large dataset of intensive care patient data to predict mortality and show that we can extract expert knowledge using an online platform, help reveal hidden confounders, improve generalizability on a different population and learn using less data. EAML presents a novel framework for high performance and dependable machine learning in critical applications.