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.
New algorithms improve causal direction inference accuracy using parallel ensemble methods.
TARP tests accuracy of generative posterior estimators.
Approximate probabilistic inference algorithms are central to many fields. Examples include sequential Monte Carlo inference in robotics, variational inference in machine learning, and Markov chain Monte Carlo inference in statistics. A key problem faced by practitioners is measuring the accuracy of an approximate infe…
In likelihood-free settings where likelihood evaluations are intractable, approximate Bayesian computation (ABC) addresses the formidable inference task to discover plausible parameters of simulation programs that explain the observations. However, they demand large quantities of simulation calls. Critically, hyperpara…
Paper monitors DNN accuracy to enhance trustworthiness.
We develop a novel method, called PoWER-BERT, for improving the inference time of the popular BERT model, while maintaining the accuracy. It works by: a) exploiting redundancy pertaining to word-vectors (intermediate encoder outputs) and eliminating the redundant vectors. b) determining which word-vectors to eliminate …
Adaptive workflow combines fast amortized inference with MCMC for many datasets.
CryptoNAS improves PI accuracy by 3.4% with 2.4x less latency.
SNVI combines likelihood estimation with variational inference for efficient Bayesian inference.
We propose a generic framework to calibrate accuracy and confidence of a prediction in deep neural networks through stochastic inferences. We interpret stochastic regularization using a Bayesian model, and analyze the relation between predictive uncertainty of networks and variance of the prediction scores obtained by …
We study the tradeoff between computational effort and classification accuracy in a cascade of deep neural networks. During inference, the user sets the acceptable accuracy degradation which then automatically determines confidence thresholds for the intermediate classifiers. As soon as the confidence threshold is met,…
In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model compression and architecture search to learn models that are resource-efficient a…
TIP-Search optimizes market prediction accuracy and timeliness under uncertain load.
Bayesian neural networks struggle with accuracy and uncertainty quantification in complex models.
Network quantization is one of the most hardware friendly techniques to enable the deployment of convolutional neural networks (CNNs) on low-power mobile devices. Recent network quantization techniques quantize each weight kernel in a convolutional layer independently for higher inference accuracy, since the weight ker…
As neural networks become widely deployed in different applications and on different hardware, it has become increasingly important to optimize inference time and model size along with model accuracy. Most current techniques optimize model size, model accuracy and inference time in different stages, resulting in subopt…
Active sampling algorithm improves accuracy of inferred scores from pairwise comparisons.
Freezing intermediate layers reduces DNN inference latency.
Bayesian inference improves neural network predictions by separating aleatoric and epistemic uncertainties.
Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications. To mitigate these threats, we propose mechanisms to transform sensor data before sharing them with applications running on users' devices. Thes…
This paper introduces a new technique for quantifying the approximation error of a broad class of probabilistic inference programs, including ones based on both variational and Monte Carlo approaches. The key idea is to derive a subjective bound on the symmetrized KL divergence between the distribution achieved by an a…
Bayesian inference improves neural network pruning efficiency.
In this paper we present a comprehensive view of prominent causal discovery algorithms, categorized into two main categories (1) assuming acyclic and no latent variables, and (2) allowing both cycles and latent variables, along with experimental results comparing them from three perspectives: (a) structural accuracy, (…
A wide variety of deep neural applications increasingly rely on the cloud to perform their compute-heavy inference. This common practice requires sending private and privileged data over the network to remote servers, exposing it to the service provider and potentially compromising its privacy. Even if the provider is …
Paper proposes a new binary quantization method for faster DNN inference.
Improved CNN accuracy for encrypted data using approximate activation functions.
BBNN improves neural network accuracy and uncertainty quantification.
Recent work used importance sampling ideas for better variational bounds on likelihoods. We clarify the applicability of these ideas to pure probabilistic inference, by showing the resulting Importance Weighted Variational Inference (IWVI) technique is an instance of augmented variational inference, thus identifying th…
APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.
The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be carried out using integer-only arithmetic, which can be implemented more efficie…
TripDecoder recovers metro routes and travel times from smart card data.
The paper studies how to improve language model inference using particle filtering.
This work optimizes DNN inference for energy-harvesting devices by compressing and selectively executing neural network exits.
Bayesian predictive inference analyzes a dataset to make predictions about new observations. When a model does not match the data, predictive accuracy suffers. We develop population empirical Bayes (POP-EB), a hierarchical framework that explicitly models the empirical population distribution as part of Bayesian analys…
Test log-likelihood comparisons can be misleading.
Inference of gene regulatory network from expression data is a challenging task. Many methods have been developed to this purpose but a comprehensive evaluation that covers unsupervised, semi-supervised and supervised methods, and provides guidelines for their practical application, is lacking. We performed an extensiv…
Study compares federated learning and coreset approaches for privacy in distributed machine learning.
Structured prediction energy networks (SPENs; Belanger & McCallum 2016) use neural network architectures to define energy functions that can capture arbitrary dependencies among parts of structured outputs. Prior work used gradient descent for inference, relaxing the structured output to a set of continuous variables a…
We derive streamlined mean field variational Bayes algorithms for fitting linear mixed models with crossed random effects. In the most general situation, where the dimensions of the crossed groups are arbitrarily large, streamlining is hindered by lack of sparseness in the underlying least squares system. Because of th…
CMPE improves SBI efficiency and accuracy.
IoT nodes compress measurements into DNN outputs for efficient communication.
DeepRV accelerates spatiotemporal inference using neural priors.
The paper proposes an efficient method to scale Bayesian inference for mixed multinomial logit models to very large datasets.
New method uses low-fidelity simulations to efficiently infer parameters of high-fidelity models.
Bayesian design improves accuracy without extra cost.
Enhances SBI accuracy with multilevel Monte Carlo for expensive simulators.
Kaleidoscope matrices improve model quality and inference speed.
Linear cost method approximates Gaussian Matérn processes with exponentially convergent accuracy.