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.
G-Net constructs binary neural networks with high accuracy using randomized binary embeddings.
Automatic debiasing for causal and policy effects using Neural Nets and Random Forests.
Bonsai-Net efficiently discovers state-of-the-art models with fewer parameters.
RODE-Net learns ODEs from data with random parameters using neural networks and GANs.
Bayesian method improves neural net convergence for character recognition.
Random neural nets learn Black-Scholes PDEs without dimensionality issues.
Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and provides the following improvements over recent works: (i) Using a tighter char…
Understanding the learning dynamics of neural networks is one of the key issues for the improvement of optimization algorithms as well as for the theoretical comprehension of why deep neural nets work so well today. In this paper, we introduce a random matrix-based framework to analyze the learning dynamics of a single…
Parameter reduction has been an important topic in deep learning due to the ever-increasing size of deep neural network models and the need to train and run them on resource limited machines. Despite many efforts in this area, there were no rigorous theoretical guarantees on why existing neural net compression methods …
U-Net trained to recover acoustic interference striations from distorted data.
Image reconstruction in low-count PET is particularly challenging because gammas from natural radioactivity in Lu-based crystals cause high random fractions that lower the measurement signal-to-noise-ratio (SNR). In model-based image reconstruction (MBIR), using more iterations of an unregularized method may increase t…
We prove overfitting in minimal and random NNs, tempering the effect.
We give algorithms with provable guarantees that learn a class of deep nets in the generative model view popularized by Hinton and others. Our generative model is an node multilayer neural net that has degree at most for some and each edge has a random edge weight in . Our algorithm learns {\em …
Deep neural nets approximate random dynamical system trajectories uniformly in time.
Proposes a novel neural network method to estimate average treatment effect.
Although artificial neural networks have occasionally been used for Quantitative Structure-Activity/Property Relationship (QSAR/QSPR) studies in the past, the literature has of late been dominated by other machine learning techniques such as random forests. However, a variety of new neural net techniques along with suc…
Deep networks, especially convolutional neural networks (CNNs), have been successfully applied in various areas of machine learning as well as to challenging problems in other scientific and engineering fields. This paper introduces Butterfly-Net, a low-complexity CNN with structured and sparse cross-channel connection…
Recent research shows that the following two models are equivalent: (a) infinitely wide neural networks (NNs) trained under l2 loss by gradient descent with infinitesimally small learning rate (b) kernel regression with respect to so-called Neural Tangent Kernels (NTKs) (Jacot et al., 2018). An efficient algorithm to c…
An important class of distance metrics proposed for training generative adversarial networks (GANs) is the integral probability metric (IPM), in which the neural net distance captures the practical GAN training via two neural networks. This paper investigates the minimax estimation problem of the neural net distance ba…
New bounds explain deterministic non-smooth deep nets without large Lipschitz constants.
New algorithm interpolates data with neural nets, independent of sample size.
The general perception is that kernel methods are not scalable, and neural nets are the methods of choice for nonlinear learning problems. Or have we simply not tried hard enough for kernel methods? Here we propose an approach that scales up kernel methods using a novel concept called "doubly stochastic functional grad…
Study examines how classifier performance is affected by training data quality.
Despite the phenomenal success of deep learning in recent years, there remains a gap in understanding the fundamental mechanics of neural nets. More research is focussed on handcrafting complex and larger networks, and the design decisions are often ad-hoc and based on intuition. Some recent research has aimed to demys…
In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a …
Randomized neural networks improve exposure and CVA estimation for American options.
GIT-Net uses neural networks to approximate PDE operators efficiently.
We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness of neural networks (Liu 2017), we noticed that adding noise blindly to all the la…
DP-Net uses dynamic programming for efficient deep neural network compression.
Study measures impact of data and neural net similarity on transferability in restaurant sales data.
Mean-field neural nets approximate functions using a free energy functional and controlled dynamics.
Learning to Optimize is a recently proposed framework for learning optimization algorithms using reinforcement learning. In this paper, we explore learning an optimization algorithm for training shallow neural nets. Such high-dimensional stochastic optimization problems present interesting challenges for existing reinf…
Bandlimited random neural networks may not approximate all functions perfectly.
This paper considers the power of deep neural networks (deep nets for short) in realizing data features. Based on refined covering number estimates, we find that, to realize some complex data features, deep nets can improve the performances of shallow neural networks (shallow nets for short) without requiring additiona…
DNF-Net tackles tabular data challenges with neural architecture.
Deep neural nets solve complex insurance math equations.
SDE-Net quantifies uncertainty in deep nets using stochastic dynamics.
White matter hyperintensity (WMH) is commonly found in elder individuals and appears to be associated with brain diseases. U-net is a convolutional network that has been widely used for biomedical image segmentation. Recently, U-net has been successfully applied to WMH segmentation. Random initialization is usally used…
FEA-Net uses physics knowledge to predict material responses efficiently.
We derive generalization and excess risk bounds for neural nets using a family of complexity measures based on a multilevel relative entropy. The bounds are obtained by introducing the notion of generated hierarchical coverings of neural nets and by using the technique of chaining mutual information introduced in Asadi…
fSDE-Net generates time series with long-term memory using neural networks.
New algorithm reduces neural net error in contextual bandits.
R2D2-Net improves Bayesian neural networks by preventing over-shrinkage of important weights.
Proposes -Nets, polynomial neural networks, for improved representation power.
Recent works have shown that on sufficiently over-parametrized neural nets, gradient descent with relatively large initialization optimizes a prediction function in the RKHS of the Neural Tangent Kernel (NTK). This analysis leads to global convergence results but does not work when there is a standard regulari…
Study on how reparametrization affects neural nets' parameter spaces from a geometric perspective.
Unified framework for U-Net design and analysis.
Based on the tree architecture, the objective of this paper is to design deep neural networks with two or more hidden layers (called deep nets) for realization of radial functions so as to enable rotational invariance for near-optimal function approximation in an arbitrarily high dimensional Euclidian space. It is show…