arXiv research

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

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 …

Efficiently calibrates volatility models using Chebyshev Tensors.

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

Delay-SDE-net models time series with memory and uncertainty, outperforming other models.

Metrics assess uncertainty structure and distribution for regression models.

This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a plan…

In this work, we propose a novel meta-learning approach for few-shot classification, which learns transferable prior knowledge across tasks and directly produces network parameters for similar unseen tasks with training samples. Our approach, called LGM-Net, includes two key modules, namely, TargetNet and MetaNet. The …

As machine learning is applied to an increasing variety of complex problems, which are defined by high dimensional and complex data sets, the necessity for task oriented feature learning grows in importance. With the advancement of Deep Learning algorithms, various successful feature learning techniques have evolved. I…

C2G-Net improves image classification of similar objects like cells.

Generative neural nets learn deep policies conditioned on goals.

Visualizes classification accuracy and label bias in neural nets and trees.

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…

Convolutional nets require fewer samples than fully-connected nets for image classification.

Recently, graph neural networks have been adopted in a wide variety of applications ranging from relational representations to modeling irregular data domains such as point clouds and social graphs. However, the space of graph neural network architectures remains highly fragmented impeding the development of optimized …

Deep Bayesian neural nets can use simpler weight approximations without sacrificing performance.

EASIER-net uses sparse networks to improve prediction accuracy for high-dimensional data.

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…

We develop a fast, tractable technique called Net-Trim for simplifying a trained neural network. The method is a convex post-processing module, which prunes (sparsifies) a trained network layer by layer, while preserving the internal responses. We present a comprehensive analysis of Net-Trim from both the algorithmic a…

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 …

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

Neural net reweighing improves selectivity in molecule binding studies.

The study examines how shallow neural nets converge to training samples or manifold points during diffusion.

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

Our work connects parameter magnitudes and Hessian eigenspaces in deep neural nets.

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…

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…

FGNNs improve game-playing AI by exploiting symmetries.

DNF-Net tackles tabular data challenges with neural architecture.

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

Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples - a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to misclassify. Existing methods for crafting adversarial examples are based on $L_2$ and $L_\infty$ distortion me…

New algorithm optimizes tessellated kernels for larger datasets and improved performance.

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.

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…

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…

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

Proposes EE-Net for neural exploration in contextual bandits.

Study uses neural networks to predict wall quantities in turbulent flows.

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.

Neural net reconstructs dark matter density from halo velocities.

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…

Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolutional networks (convnets), incorporating rectifier units and max-pooling, are neither smooth nor convex. Standard guarantees therefore do n…