arXiv research

Stochastic momentum methods trade compute efficiency for serial runtime.

The event-driven and elastic nature of serverless runtimes makes them a very efficient and cost-effective alternative for scaling up computations. So far, they have mostly been used for stateless, data parallel and ephemeral computations. In this work, we propose using serverless runtimes to solve generic, large-scale …

New method for valid prediction intervals in counterfactual outcomes with runtime confounding.

d3p package enables efficient Bayesian inference with differential privacy.

We present any-precision deep neural networks (DNNs), which are trained with a new method that allows the learned DNNs to be flexible in numerical precision during inference. The same model in runtime can be flexibly and directly set to different bit-widths, by truncating the least significant bits, to support dynamic …

QBSD optimizes KPI forecasting for RAN networks with fast runtime and accuracy.

A new algorithm reduces online exp-concave optimization runtime.

GNMR controls runtime stability in low-precision language model training.

Sparse deep neural networks(DNNs) are efficient in both memory and compute when compared to dense DNNs. But due to irregularity in computation of sparse DNNs, their efficiencies are much lower than that of dense DNNs on regular parallel hardware such as TPU. This inefficiency leads to poor/no performance benefits for s…

FLAME auto-labels mobile data efficiently on diverse processors.

"How much energy is consumed for an inference made by a convolutional neural network (CNN)?" With the increased popularity of CNNs deployed on the wide-spectrum of platforms (from mobile devices to workstations), the answer to this question has drawn significant attention. From lengthening battery life of mobile device…

Improved EXACT strategy reduces GNN memory consumption and runtime.

New DP algorithm improves privacy and efficiency for convex optimization.

Developed efficient distributed logistic regression for large datasets.

We present a novel algorithm, Westfall-Young light, for detecting patterns, such as itemsets and subgraphs, which are statistically significantly enriched in one of two classes. Our method corrects rigorously for multiple hypothesis testing and correlations between patterns through the Westfall-Young permutation proced…

SDSR reconstructs species trees from genetic markers efficiently.

New algorithm reduces runtime for robust sparse mean estimation.

Predicting the runtime complexity of a programming code is an arduous task. In fact, even for humans, it requires a subtle analysis and comprehensive knowledge of algorithms to predict time complexity with high fidelity, given any code. As per Turing's Halting problem proof, estimating code complexity is mathematically…

Some methods based on simple regularizing geometric element transformations have heuristically been shown to give runtime efficient and quality effective smoothing algorithms for meshes. We describe the mathematical framework and a systematic approach to global optimization-based versions of such methods for mixed volu…

NPOD algorithm improves efficiency in estimating pharmacokinetic parameters.

Model predicts counterfactuals under domain shift and inaccessible variables.

A new method estimates generative model mappings using kernel transfer operators, reducing costs and improving performance.

We develop and analyze efficient "coordinate-wise" methods for finding the leading eigenvector, where each step involves only a vector-vector product. We establish global convergence with overall runtime guarantees that are at least as good as Lanczos's method and dominate it for slowly decaying spectrum. Our methods a…

Paper accelerates conformal prediction by using approximate leave-one-out estimators.

Efficiently solves large portfolio optimization problems by reducing and sparsifying covariance matrices.

A distributed algorithm for online multi-task learning reduces communication and runtime costs.

Improved biclustering algorithm reduces memory usage and runtime.

Improved computational efficiency for estimating Wasserstein distance.

We consider the problem of configuring general-purpose solvers to run efficiently on problem instances drawn from an unknown distribution. The goal of the configurator is to find a configuration that runs fast on average on most instances, and do so with the least amount of total work. It can run a chosen solver on a r…

ZICO learns DAGs from zero-inflated count data efficiently.

Proposes RBGP framework for efficient block sparse neural networks.

This paper explains the theoretical inductive bias of Isolation Forest.

Efficiently approximates Sparse PCA with significant speedups and minor error.

Vecchia approximations provide the best accuracy-runtime trade-off for Gaussian process approximations.

Paper tackles efficient IRL in offline settings with polynomial samples and runtime.

New algorithm scales NDPP learning and inference to large item collections.

Long Short-Term Memory (LSTM) is a popular approach to boosting the ability of Recurrent Neural Networks to store longer term temporal information. The capacity of an LSTM network can be increased by widening and adding layers. However, usually the former introduces additional parameters, while the latter increases the…

Bayesian method predicts runtime metrics for fog manufacturing.

The runtime for Kernel Partial Least Squares (KPLS) to compute the fit is quadratic in the number of examples. However, the necessity of obtaining sensitivity measures as degrees of freedom for model selection or confidence intervals for more detailed analysis requires cubic runtime, and thus constitutes a computationa…

Matrix completion, where we wish to recover a low rank matrix by observing a few entries from it, is a widely studied problem in both theory and practice with wide applications. Most of the provable algorithms so far on this problem have been restricted to the offline setting where they provide an estimate of the unkno…

Asynchronous SGD can speed up training with a trade-off of gradient staleness.

Bayesian rating system for large competitions improves prediction and efficiency.

Algorithm identifies probability distributions from noisy moments with minimal samples.

Develops a game-theoretic approach to solve SGEP efficiently.

Algorithm decides if two hyperbolic 3-manifolds are homeomorphic.

RIn-Close_CVC is an efficient (take polynomial time per bicluster), complete (find all maximal biclusters), correct (all biclusters attend the user-defined level of consistency) and non-redundant (all the obtained biclusters are maximal and the same bicluster is not enumerated more than once) enumerative algorithm for …

Efficiently discovers causal DAG permutations without additional assumptions.

Daydream predicts DNN optimization efficacy efficiently.