arXiv research

Paper finds the best way to estimate neural net distance from samples.

New neural nets respect triangle inequality, improving graph and reinforcement learning performance.

Improved training boosts certified robustness of L-infinity distance nets.

The paper connects geodesic nets to distance function critical points.

Neural net reweighing improves selectivity in molecule binding studies.

G-Net constructs binary neural networks with high accuracy using randomized binary embeddings.

Euclidean nets reveal properties of higher-dimensional manifolds.

In human cognition, the expansion of perceived between-category distances and compression of within-category distances is known as categorical perception (CP). There are several hypotheses about the causes of CP (e.g., language, learning, evolution) but no functional model. Whether CP is essential to categorisation or …

We show that training of generative adversarial network (GAN) may not have good generalization properties; e.g., training may appear successful but the trained distribution may be far from target distribution in standard metrics. However, generalization does occur for a weaker metric called neural net distance. It is a…

This research explores the dynamics of linearised neural nets, revealing distinct learning phases and layer growth rates.

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 …

The paper evaluates and improves uncertainty estimates in neural networks for safety-critical applications.

New training method for neural nets using multilevel entropic regularization.

GIT-Net uses neural networks to approximate PDE operators efficiently.

Bayesian ReLU nets fix asymptotic overconfidence with infinite features.

Preference are central to decision making by both machines and humans. Representing, learning, and reasoning with preferences is an important area of study both within computer science and across the sciences. When working with preferences it is necessary to understand and compute the distance between sets of objects, …

DP-Net uses dynamic programming for efficient deep neural network compression.

Deep nets improve function approximation and learning in high dimensions.

Deep nets outperform shallow nets in complex feature realization.

Study measures impact of data and neural net similarity on transferability in restaurant sales data.

RadiX-Net generates diverse sparse neural topologies.

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…

DNF-Net tackles tabular data challenges with neural architecture.

SDE-Net quantifies uncertainty in deep nets using stochastic dynamics.

The paper provides theoretical guarantees for hashing-based neural net compression.

CPOPT-Net predicts sparse client actions in banking using tensor decomposition and neural networks.

Researchers prove NP-hardness of learning parameter-bounded Bayes nets.

fSDE-Net generates time series with long-term memory using neural networks.

New algorithm reduces neural net error in contextual bandits.

Proposes $Π$-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 $\ell_2$ regulari…

Rigidity theorem for discrete metric spaces embedded in Riemannian surfaces.

Study on how reparametrization affects neural nets' parameter spaces from a geometric perspective.

Unified framework for U-Net design and analysis.

Proposes EE-Net for neural exploration in contextual bandits.

New tool for interpreting neural nets, explaining model behavior.

IntraVascular UltraSound (IVUS) is one of the most effective imaging modalities that provides assistance to experts in order to diagnose and treat cardiovascular diseases. We address a central problem in IVUS image analysis with Fully Convolutional Network (FCN): automatically delineate the lumen and media-adventitia b…

While Generative Adversarial Networks (GANs) have empirically produced impressive results on learning complex real-world distributions, recent works have shown that they suffer from lack of diversity or mode collapse. The theoretical work of Arora et al. suggests a dilemma about GANs' statistical properties: powerful d…

Improves neural net generalization by modeling hidden state distribution.

Electronic phenotyping is the task of ascertaining whether an individual has a medical condition of interest by analyzing their medical record and is foundational in clinical informatics. Increasingly, electronic phenotyping is performed via supervised learning. We investigate the effectiveness of multitask learning fo…

Catapult phase in neural nets shows exponential loss growth before quick decrease.

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…

Neural net reconstructs dark matter density from halo velocities.

MRAI-NET learns MRI scanner-independent features for better tissue segmentation.

Bayesian Neural Nets improve model stability and fit.

Global convergence of SGD proven for two-layer neural nets with regularization.

We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines optimal transport in primal form with an energy distance define…

Oracle inequality for sparse neural nets adapts to unknown structure.