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.
Proposes a new generalization bound for Bayesian deep nets without strict assumptions.
SDE-Net quantifies uncertainty in deep nets using stochastic dynamics.
Deep Bayesian neural nets can use simpler weight approximations without sacrificing performance.
New bounds explain deterministic non-smooth deep nets without large Lipschitz constants.
New bound relaxes uniform gradient norm assumptions for PAC-Bayesian bounds.
This thesis builds theoretical foundations for deep learning, proving complexity theorems and training algorithms.
We propose a novel method for closed-form predictive distribution modeling with neural nets. In quantifying prediction uncertainty, we build on Evidential Deep Learning, which has been impactful as being both simple to implement and giving closed-form access to predictive uncertainty. We employ it to model aleatoric un…
Two models predict net loan losses using Bayesian and frequentist regression.
Rank-1 BNNs improve efficiency and scalability of Bayesian neural nets.
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 …
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…
This paper improves Bayesian neural nets by using local linearization.
Deterministic neural nets have been shown to learn effective predictors on a wide range of machine learning problems. However, as the standard approach is to train the network to minimize a prediction loss, the resultant model remains ignorant to its prediction confidence. Orthogonally to Bayesian neural nets that indi…
We develop a scalable method for Bayesian neural networks with stochastic differential equations.
We describe Bayesian Layers, a module designed for fast experimentation with neural network uncertainty. It extends neural network libraries with drop-in replacements for common layers. This enables composition via a unified abstraction over deterministic and stochastic functions and allows for scalability via the unde…
BCD Nets use variational inference to estimate DAGs with uncertainty.
Bayesian method improves neural net convergence for character recognition.
DP-Net uses dynamic programming for efficient deep neural network compression.
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…
Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for Stochastic Gradient Descent (SGD). These methods improve convergence by adapting to th…
RegPred Net forecasts foreign exchange rates with improved accuracy and interpretability.
In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features. To improve the representation and clustering abilities, DSCF-Net explicitly considers discov…
PNCs balance tractability and expressiveness in probabilistic modeling.
In this paper, we develop an alternating direction method of multipliers (ADMM) for deep neural networks training with sigmoid-type activation functions (called \textit{sigmoid-ADMM pair}), mainly motivated by the gradient-free nature of ADMM in avoiding the saturation of sigmoid-type activations and the advantages of …
This paper improves ensemble learning for vision tasks by encouraging diversity in predictions.
Mode connectivity is a surprising phenomenon in the loss landscape of deep nets. Optima -- at least those discovered by gradient-based optimization -- turn out to be connected by simple paths on which the loss function is almost constant. Often, these paths can be chosen to be piece-wise linear, with as few as two segm…
Method learns invariances in deep nets without human validation.
Bayesian ReLU nets fix asymptotic overconfidence with infinite features.
Proposes HDBEN for heteroscedastic regression with improved sparsity and variance modeling.
Proposes a new deep learning model for uncertainty quantification and propagation.
This paper investigates the influence of different acoustic features, audio-events based features and automatic speech translation based lexical features in complex emotion recognition such as curiosity. Pretrained networks, namely, AudioSet Net, VoxCeleb Net and Deep Speech Net trained extensively for different speech…
GIT-Net uses neural networks to approximate PDE operators efficiently.
We are interested in the development of surrogate models for uncertainty quantification and propagation in problems governed by stochastic PDEs using a deep convolutional encoder-decoder network in a similar fashion to approaches considered in deep learning for image-to-image regression tasks. Since normal neural netwo…
Neural Ordinary Differential Equations (N-ODEs) are a powerful building block for learning systems, which extend residual networks to a continuous-time dynamical system. We propose a Bayesian version of N-ODEs that enables well-calibrated quantification of prediction uncertainty, while maintaining the expressive power …
A zoo of deep nets is available these days for almost any given task, and it is increasingly unclear which net to start with when addressing a new task, or which net to use as an initialization for fine-tuning a new model. To address this issue, in this paper, we develop knowledge flow which moves 'knowledge' from mult…
Proposes -Nets, polynomial neural networks, for improved representation power.
X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using la…
How well does a classic deep net architecture like AlexNet or VGG19 classify on a standard dataset such as CIFAR-10 when its width --- namely, number of channels in convolutional layers, and number of nodes in fully-connected internal layers --- is allowed to increase to infinity? Such questions have come to the forefr…
G-Net uses deep learning for complex counterfactual outcome prediction.
Efficient method for uncertainty estimation in DNNs with improved accuracy.
Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-for…
MPHD transfers knowledge across different domains for Bayesian optimization.
Deep learning system diagnoses AVNFH from plain radiographs.
DS2CF-Net learns hierarchical representations with deep coupled factorization and enriched prior.
HAD-Net forecasts glucose levels with insights into insulin and carbs diffusion.
Estimates individualized treatment effects using shared RBF-net neurons.
Efficiently calibrates volatility models using Chebyshev Tensors.
Meta-learning is a promising method to achieve efficient training method towards deep neural net and has been attracting increases interests in recent years. But most of the current methods are still not capable to train complex neuron net model with long-time training process. In this paper, a novel second-order meta-…