A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
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 …
Improved algorithm for optimal stopping problems reduces runtime.
In many recent applications, data is plentiful. By now, we have a rather clear understanding of how more data can be used to improve the accuracy of learning algorithms. Recently, there has been a growing interest in understanding how more data can be leveraged to reduce the required training runtime. In this paper, we…
Separating the short jobs from the long is a known technique to improve scheduling performance. In this paper we describe a method we developed for accurately predicting the runtimes classes of the jobs to enable this separation. Our method uses the fact that the runtimes can be represented as a mixture of overlapping …
Improved EXACT strategy reduces GNN memory consumption and runtime.
Training neural network often uses a machine learning framework such as TensorFlow and Caffe2. These frameworks employ a dataflow model where the NN training is modeled as a directed graph composed of a set of nodes. Operations in neural network training are typically implemented by the frameworks as primitives and rep…
Improved biclustering algorithm reduces memory usage and runtime.
GNMR controls runtime stability in low-precision language model training.
For well over a quarter century, detection systems have been driven by models learned from input features collected from real or simulated environments. An artifact (e.g., network event, potential malware sample, suspicious email) is deemed malicious or non-malicious based on its similarity to the learned model at runt…
UMFI improves feature importance methods by reducing runtime and enhancing performance.
Perhaps surprisingly, it is possible to predict how long an algorithm will take to run on a previously unseen input, using machine learning techniques to build a model of the algorithm's runtime as a function of problem-specific instance features. Such models have important applications to algorithm analysis, portfolio…
This paper presents Rudra, a parameter server based distributed computing framework tuned for training large-scale deep neural networks. Using variants of the asynchronous stochastic gradient descent algorithm we study the impact of synchronization protocol, stale gradient updates, minibatch size, learning rates, and n…
New methods improve solving linear systems and preconditioning with reduced complexity.
Model predicts counterfactuals under domain shift and inaccessible variables.
Rewiring networks using discrete geometry improves GNN training accuracy and reduces runtime.
Improved robust regression algorithms with faster runtime and better estimation rates.
Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly classified inputs are much larger than that of misclassified inputs which include adver…
A new method estimates generative model mappings using kernel transfer operators, reducing costs and improving performance.
Improved computational efficiency for estimating Wasserstein distance.
New DP algorithm improves privacy and efficiency for convex optimization.
Vecchia approximations provide the best accuracy-runtime trade-off for Gaussian process approximations.
Improves Gaussian process factor models for multi-population recordings.
We describe the concept of logical scaffolds, which can be used to improve the quality of software that relies on AI components. We explain how some of the existing ideas on runtime monitors for perception systems can be seen as a specific instance of logical scaffolds. Furthermore, we describe how logical scaffolds ma…
Bayesian method predicts runtime metrics for fog manufacturing.
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…
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…
Sublinear LSVI via LSH reduces runtime to sublinear in actions.
Asynchronous SGD can speed up training with a trade-off of gradient staleness.
"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…
Algorithm decides if two hyperbolic 3-manifolds are homeomorphic.
Improved iterative hard thresholding for faster, sparser solutions.
Developed efficient distributed logistic regression for large datasets.
New Fourier metrics equivalent to Wasserstein distances in image processing.
Bayesian optimization (BO) aims to minimize a given blackbox function using a model that is updated whenever new evidence about the function becomes available. Here, we address the problem of BO under partially right-censored response data, where in some evaluations we only obtain a lower bound on the function value. T…
We introduce several new black-box reductions that significantly improve the design of adaptive and parameter-free online learning algorithms by simplifying analysis, improving regret guarantees, and sometimes even improving runtime. We reduce parameter-free online learning to online exp-concave optimization, we reduce…
Bayesian rating system for large competitions improves prediction and efficiency.
Performing inference over simulators is generally intractable as their runtime means we cannot compute a marginal likelihood. We develop a likelihood-free inference method to infer parameters for a cardiac simulator, which replicates electrical flow through the heart to the body surface. We improve the fit of a state-o…
Stochastic Variance-Reduced Cubic regularization (SVRC) algorithms have received increasing attention due to its improved gradient/Hessian complexities (i.e., number of queries to stochastic gradient/Hessian oracles) to find local minima for nonconvex finite-sum optimization. However, it is unclear whether existing SVR…
CIT and CIF improve feature selection for downstream prediction.
Efficiently solves large portfolio optimization problems by reducing and sparsifying covariance matrices.
Improved learning bounds for corrupted data using thresholded gradient descent.
We introduce a proximal version of the stochastic dual coordinate ascent method and show how to accelerate the method using an inner-outer iteration procedure. We analyze the runtime of the framework and obtain rates that improve state-of-the-art results for various key machine learning optimization problems including …
Optimal transportation, or computing the Wasserstein or ``earth mover's'' distance between two distributions, is a fundamental primitive which arises in many learning and statistical settings. We give an algorithm which solves this problem to additive with parallel depth, and $\tilde{O}\left(n^2/ε\…
Many contemporary machine learning models require extensive tuning of hyperparameters to perform well. A variety of methods, such as Bayesian optimization, have been developed to automate and expedite this process. However, tuning remains extremely costly as it typically requires repeatedly fully training models. We pr…
We consider the problem of improving fairness when one lacks access to a dataset labeled with protected groups, making it difficult to take advantage of strategies that can improve fairness but require protected group labels, either at training or runtime. To address this, we investigate improving fairness metrics for …
New scalable MCMC sampling for nonsymmetric DPPs speeds up computations.
Improved Frank-Wolfe algorithm speeds up training of differentially private LASSO models.