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.
A neural network model minimizes region-based free energy for faster inference in MRFs.
We present a joint message passing approach that combines belief propagation and the mean field approximation. Our analysis is based on the region-based free energy approximation method proposed by Yedidia et al. We show that the message passing fixed-point equations obtained with this combination correspond to station…
Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to adversarial manipulations at testing time. Specifically, suppose we have a testing …
Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tuning, or require many iterations to solve an optimization based adversarial attack. To address this problem, we present a new family of trus…
Adaptive region-based active learning seeks labels for complex data.
We derive Gaussian approximations for random forest predictions using region-based stabilization.
Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution method, XRAI, that builds upon integrated gradients (Sundararajan et al. 2017), 2) int…
Interferometric Synthetic Aperture Radar (InSAR) imagery based on microwaves reflected off ground targets is becoming increasingly important in remote sensing for ground movement estimation. However, the reflections are contaminated by noise, which distorts the signal's wrapped phase. Demarcation of image regions based…
The lack of interpretability remains a barrier to the adoption of deep neural networks. Recently, tree regularization has been proposed to encourage deep neural networks to resemble compact, axis-aligned decision trees without significant compromises in accuracy. However, it may be unreasonable to expect that a single …
USNRT uses tree-structured learning to improve uncertainty quantification of variance networks.
Resting-state functional MRI (rs-fMRI) scans hold the potential to serve as a diagnostic or prognostic tool for a wide variety of conditions, such as autism, Alzheimer's disease, and stroke. While a growing number of studies have demonstrated the promise of machine learning algorithms for rs-fMRI based clinical or beha…
Graph neural networks are explained through energy gradient flow and framelet decomposition.
This work optimizes DNN inference for energy-harvesting devices by compressing and selectively executing neural network exits.
New attacks exploit neural network energy and latency, increasing costs by 10-200x.
Paper analyzes the free energy of CNNs with skip connections in Bayesian learning.
LNNs learn Lagrangians without canonical coordinates, conserving energy and relativity.
Deep neural networks improve free energy calculations for peptide conformations.
Improved generative models using overparametrized shallow neural networks.
We explore the energy landscape of a simple neural network. In particular, we expand upon previous work demonstrating that the empirical complexity of fitted neural networks is vastly less than a naive parameter count would suggest and that this implicit regularization is actually beneficial for generalization from fit…
Adversarial attacks can fool ML energy theft detection models.
TPBS models improve robustness to overfitting with localized Dirichlet energy regularization.
Dual training method for EBMs with overparametrized neural networks.
Bayesian free energy remains bounded for deep ReLU networks in overparametrized cases.
Graph neural networks over-smooth when layers increase, reducing discriminative power.
New algorithms improve contextual bandits with neural networks and energy models.
Novel method combines physics priors for energy-conserving dynamics.
Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be reduced at the cost of reduced reliability. A training algorithm is proposed to optim…
Dual model combines HMM and neural networks for energy trading during volatile periods.
POET enables large neural network training on tiny devices with reduced energy.
We implement a differentiable Neural Architecture Search (NAS) method inspired by FBNet for discovering neural networks that are heavily optimized for a particular target device. The FBNet NAS method discovers a neural network from a given search space by optimizing over a loss function which accounts for accuracy and …
We introduce the Hierarchically Interacting Particle Neural Network (HIP-NN) to model molecular properties from datasets of quantum calculations. Inspired by a many-body expansion, HIP-NN decomposes properties, such as energy, as a sum over hierarchical terms. These terms are generated from a neural network--a composit…
The specificty and sensitivity of resting state functional MRI (rs-fMRI) measurements depend on pre-processing choices, such as the parcellation scheme used to define regions of interest (ROIs). In this study, we critically evaluate the effect of brain parcellations on machine learning models applied to rs-fMRI data. O…
Improved SNNs with quantized activations outperform traditional networks.
Many practical machine learning tasks employ very deep convolutional neural networks. Such large depths pose formidable computational challenges in training and operating the network. It is therefore important to understand how fast the energy contained in the propagated signals (a.k.a. feature maps) decays across laye…
Training neural networks involves finding minima of a high-dimensional non-convex loss function. Knowledge of the structure of this energy landscape is sparse. Relaxing from linear interpolations, we construct continuous paths between minima of recent neural network architectures on CIFAR10 and CIFAR100. Surprisingly, …
Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited. Recently, Liu et al. (2019) framed the search of efficient neural architectures into a continuous splitting process: it itera…
Gaining more comprehensive knowledge about drug-drug interactions (DDIs) is one of the most important tasks in drug development and medical practice. Recently graph neural networks have achieved great success in this task by modeling drugs as nodes and drug-drug interactions as links and casting DDI predictions as link…
GEBM improves uncertainty quantification in graph neural networks.
Bayesian GNNs with temperature improve prediction efficiency in CP.
DeepONet learns operators for PDEs with varying parameters and initial conditions.
EDCompress optimizes energy efficiency of CNN models on edge devices.
This paper reviews methods to create compact neural networks for IoT applications.
NNs accurately predict energy eigenvalues and other physical phenomena in 1D quantum mechanics.
Paper proposes new loss functions for training energy networks.
Neural networks are a powerful class of nonlinear functions that can be trained end-to-end on various applications. While the over-parametrization nature in many neural networks renders the ability to fit complex functions and the strong representation power to handle challenging tasks, it also leads to highly correlat…
Neural network predicts daily power consumption with high accuracy.
New method uses neural networks to improve free energy estimation.
This work develops a novel power control framework for energy-efficient power control in wireless networks. The proposed method is a new branch-and-bound procedure based on problem-specific bounds for energy-efficiency maximization that allow for faster convergence. This enables to find the global solution for all of t…