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.
Natural graph networks are a new class of graph neural networks that are more flexible and scalable.
Natural gradient simplification for deep learning networks.
Hardness proven for neural networks with natural weights.
Optimizes graph neural networks using natural gradient descent.
We present a novel algorithm to train a deep Q-learning agent using natural-gradient techniques. We compare the original deep Q-network (DQN) algorithm to its natural-gradient counterpart, which we refer to as NGDQN, on a collection of classic control domains. Without employing target networks, NGDQN significantly outp…
Natural gradient descent is a robust optimization method for machine learning.
Study reveals differences in medical image models' hidden representation refinement.
The tail of a quantum spin network in the two-sphere is a -series associated to the network. We study the existence of the head and tail functions of quantum spin networks colored by . We compute the -series for an infinite family of quantum spin networks and give the relation between the tail of these networ…
MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory an…
Natural gradient descent has proven effective at mitigating the effects of pathological curvature in neural network optimization, but little is known theoretically about its convergence properties, especially for \emph{nonlinear} networks. In this work, we analyze for the first time the speed of convergence of natural …
Solves POMDPs with recurrent neural networks and natural policy gradient.
We introduce Natural Neural Networks, a novel family of algorithms that speed up convergence by adapting their internal representation during training to improve conditioning of the Fisher matrix. In particular, we show a specific example that employs a simple and efficient reparametrization of the neural network weigh…
This is a lecture note for the course DS-GA 3001 <Natural Language Understanding with Distributed Representation> at the Center for Data Science , New York University in Fall, 2015. As the name of the course suggests, this lecture note introduces readers to a neural network based approach to natural language understand…
Matrix product states (MPS), a tensor network designed for one-dimensional quantum systems, has been recently proposed for generative modeling of natural data (such as images) in terms of `Born machine'. However, the exponential decay of correlation in MPS restricts its representation power heavily for modeling complex…
Untrained neural networks can recover natural images from few measurements.
We provide several new depth-based separation results for feed-forward neural networks, proving that various types of simple and natural functions can be better approximated using deeper networks than shallower ones, even if the shallower networks are much larger. This includes indicators of balls and ellipses; non-lin…
Networks are a natural representation of complex systems across the sciences, and higher-order dependencies are central to the understanding and modeling of these systems. However, in many practical applications such as online social networks, networks are massive, dynamic, and naturally streaming, where pairwise inter…
AOPU stabilizes NN training by approximating natural gradient, improving stability and convergence.
Graph Attention Networks predict power outage durations from natural disasters.
Paper analyzes NAC with neural networks for efficient policy optimization.
Lie groupoid equivariant neural networks are a new type of neural network.
Energy-efficient detection of natural errors in deep networks.
Enhances neural network solvers for PDEs with complex boundary conditions.
Natural gradient descent avoids the magic of model parametrization, leading to different optimization outcomes.
This paper introduces metrics to evaluate robustness of neural networks to natural adversarial examples.
Most neural networks are trained using first-order optimization methods, which are sensitive to the parameterization of the model. Natural gradient descent is invariant to smooth reparameterizations because it is defined in a coordinate-free way, but tractable approximations are typically defined in terms of coordinate…
Enhanced transformer converts whispered speech to natural speech.
SONet stabilizes ODE networks for robustness without adversarial training.
Wider networks improve natural accuracy but worsen perturbation stability, affecting overall robustness.
Proposes model-based robust deep learning to handle natural variation in data.
In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws intrinsic to the network structures. To address this problem and improve the robustness …
Natural language processing (NLP) can be done using either top-down (theory driven) and bottom-up (data driven) approaches, which we call mechanistic and phenomenological respectively. The approaches are frequently considered to stand in opposition to each other. Examining some recent approaches in deep learning we arg…
Graphs represent natural and artificial systems; ML can learn from them.
Upper bound on CRN reaction rates derived using information geometry.
The study analyzes optimization trajectories in neural networks to reveal redundancy and redundancy-reducing strategies.
Two novel distributed VB algorithms improve Bayesian inference in sensor networks.
It is well-known that neural networks are universal approximators, but that deeper networks tend in practice to be more powerful than shallower ones. We shed light on this by proving that the total number of neurons required to approximate natural classes of multivariate polynomials of variables grows only line…
Neural networks (NN) have achieved state-of-the-art performance in various applications. Unfortunately in applications where training data is insufficient, they are often prone to overfitting. One effective way to alleviate this problem is to exploit the Bayesian approach by using Bayesian neural networks (BNN). Anothe…
Taking inspiration from biological evolution, we explore the idea of "Can deep neural networks evolve naturally over successive generations into highly efficient deep neural networks?" by introducing the notion of synthesizing new highly efficient, yet powerful deep neural networks over successive generations via an ev…
This work introduces a tensor-based method to perform supervised classification on spatiotemporal data processed in an echo state network. Typically when performing supervised classification tasks on data processed in an echo state network, the entire collection of hidden layer node states from the training dataset is …
Recent efforts on combining deep models with probabilistic graphical models are promising in providing flexible models that are also easy to interpret. We propose a variational message-passing algorithm for variational inference in such models. We make three contributions. First, we propose structured inference network…
Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation functions. Various new activation functions and improvements on ReLU have been proposed, but each carry performance drawbacks. In this paper, w…
We present here a new model and algorithm which performs an efficient Natural gradient descent for Multilayer Perceptrons. Natural gradient descent was originally proposed from a point of view of information geometry, and it performs the steepest descent updates on manifolds in a Riemannian space. In particular, we ext…
Modified training direction reduces generalization error in neural networks.
This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by an arbitrary graph. Such structured sequences can represent series of frames in v…
We show new connections between adversarial learning and explainability for deep neural networks (DNNs). One form of explanation of the output of a neural network model in terms of its input features, is a vector of feature-attributions. Two desirable characteristics of an attribution-based explanation are: (1) $\texti…
Multilayer switch networks are proposed as artificial generators of high-dimensional discrete data (e.g., binary vectors, categorical data, natural language, network log files, and discrete-valued time series). Unlike deconvolution networks which generate continuous-valued data and which consist of upsampling filters a…
Statistical models of natural stimuli provide an important tool for researchers in the fields of machine learning and computational neuroscience. A canonical way to quantitatively assess and compare the performance of statistical models is given by the likelihood. One class of statistical models which has recently gain…