Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to nonfederal websites. Their policies may differ from this site.

Daumé, Hal ; Singh, Aarti (Ed.)Sensitive attributes such as race are rarely available to learners in real world settings as their collection is often restricted by laws and regulations. We give a scheme that allows individuals to release their sensitive information privately while still allowing any downstream entity to learn nondiscriminatory predictors. We show how to adapt nondiscriminatory learners to work with privatized protected attributes giving theoretical guarantees on performance. Finally, we highlight how the methodology could apply to learning fair predictors in settings where protected attributes are only available for a subset of the data.more » « less

III, Hal Daumé ; Singh, Aarti (Ed.)Policy learning using historical observational data is an important problem that has found widespread applications. However, existing literature rests on the crucial assumption that the future environment where the learned policy will be deployed is the same as the past environment that has generated the data{–}an assumption that is often false or too coarse an approximation. In this paper, we lift this assumption and aim to learn a distributionally robust policy with bandit observational data. We propose a novel learning algorithm that is able to learn a robust policy to adversarial perturbations and unknown covariate shifts. We first present a policy evaluation procedure in an ambiguous environment and also give a heuristic algorithm to solve the distributionally robust policy learning problems efficiently. Additionally, we provide extensive simulations to demonstrate the robustness of our policy.more » « less

Daumé, Hal III ; Singh, Aarti (Ed.)

III, Hal Daumé ; Singh, Aarti (Ed.)Studying the set of exact solutions of a system of polynomial equations largely depends on a single iterative algorithm, known as Buchberger’s algorithm. Optimized versions of this algorithm are crucial for many computer algebra systems (e.g., Mathematica, Maple, Sage). We introduce a new approach to Buchberger’s algorithm that uses reinforcement learning agents to perform Spair selection, a key step in the algorithm. We then study how the difficulty of the problem depends on the choices of domain and distribution of polynomials, about which little is known. Finally, we train a policy model using proximal policy optimization (PPO) to learn Spair selection strategies for random systems of binomial equations. In certain domains, the trained model outperforms stateoftheart selection heuristics in total number of polynomial additions performed, which provides a proofofconcept that recent developments in machine learning have the potential to improve performance of algorithms in symbolic computation.more » « less

III, Hal Daumé ; Singh, Aarti (Ed.)Embedding computation in molecular contexts incompatible with traditional electronics is expected to have wide ranging impact in synthetic biology, medicine, nanofabrication and other fields. A key remaining challenge lies in developing programming paradigms for molecular computation that are wellaligned with the underlying chemical hardware and do not attempt to shoehorn illfitting electronics paradigms. We discover a surprisingly tight connection between a popular class of neural networks (binaryweight ReLU aka BinaryConnect) and a class of coupled chemical reactions that are absolutely robust to reaction rates. The robustness of rateindependent chemical computation makes it a promising target for bioengineering implementation. We show how a BinaryConnect neural network trained in silico using wellfounded deep learning optimization techniques, can be compiled to an equivalent chemical reaction network, providing a novel molecular programming paradigm. We illustrate such translation on the paradigmatic IRIS and MNIST datasets. Toward intended applications of chemical computation, we further use our method to generate a chemical reaction network that can discriminate between different virus types based on gene expression levels. Our work sets the stage for rich knowledge transfer between neural network and molecular programming communities.more » « less

Daumé III, Hal ; Singh, Aarti (Ed.)Thompson sampling for multiarmed bandit problems is known to enjoy favorable performance in both theory and practice. However, its wider deployment is restricted due to a significant computational limitation: the need for samples from posterior distributions at every iteration. In practice, this limitation is alleviated by making use of approximate sampling methods, yet provably incorporating approximate samples into Thompson Sampling algorithms remains an open problem. In this work we address this by proposing two efficient Langevin MCMC algorithms tailored to Thompson sampling. The resulting approximate Thompson Sampling algorithms are efficiently implementable and provably achieve optimal instancedependent regret for the MultiArmed Bandit (MAB) problem. To prove these results we derive novel posterior concentration bounds and MCMC convergence rates for logconcave distributions which may be of independent interest.more » « less

Daumé III, Hal ; Singh, Aarti (Ed.)Learning with noisy labels is a common challenge in supervised learning. Existing approaches often require practitioners to specify noise rates, i.e., a set of parameters controlling the severity of label noises in the problem, and the specifications are either assumed to be given or estimated using additional steps. In this work, we introduce a new family of loss functions that we name as peer loss functions, which enables learning from noisy labels and does not require a priori specification of the noise rates. Peer loss functions work within the standard empirical risk minimization (ERM) framework. We show that, under mild conditions, performing ERM with peer loss functions on the noisy data leads to the optimal or a nearoptimal classifier as if performing ERM over the clean training data, which we do not have access to. We pair our results with an extensive set of experiments. Peer loss provides a way to simplify model development when facing potentially noisy training labels, and can be promoted as a robust candidate loss function in such situations.more » « less

Daumé III, Hal ; Singh, Aarti (Ed.)We prove quantitative convergence rates at which discrete Langevinlike processes converge to the invariant distribution of a related stochastic differential equation. We study the setup where the additive noise can be nonGaussian and statedependent and the potential function can be nonconvex. We show that the key properties of these processes depend on the potential function and the second moment of the additive noise. We apply our theoretical findings to studying the convergence of Stochastic Gradient Descent (SGD) for nonconvex problems and corroborate them with experiments using SGD to train deep neural networks on the CIFAR10 dataset.more » « less