University of Wisconsin-Madison

∙ Madison , United States ∙ 0 followers

The University of Wisconsin–Madison is a public land-grant university and prolific research institution. Our students, staff, and faculty members partake in a world-class education and solve real-world problems.

Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence

Smarter applications are making better use of the insights gleaned from ...
02/12/2020 ∙ by Sebastian Raschka, et al. ∙ 156 ∙ share

read it
Impact of On-Chip Interconnect on In-Memory Acceleration of Deep Neural Networks

With the widespread use of Deep Neural Networks (DNNs), machine learning...
07/06/2021 ∙ by Gokul Krishnan, et al. ∙ 53 ∙ share

read it
Recent Advances in Algorithmic High-Dimensional Robust Statistics

Learning in the presence of outliers is a fundamental problem in statist...
11/14/2019 ∙ by Ilias Diakonikolas, et al. ∙ 39 ∙ share

read it
TOCO: A Framework for Compressing Neural Network Models Based on Tolerance Analysis

Neural network compression methods have enabled deploying large models o...
12/18/2019 ∙ by Soroosh Khoram, et al. ∙ 34 ∙ share

read it
Generating Semantic Adversarial Examples with Differentiable Rendering

Machine learning (ML) algorithms, especially deep neural networks, have ...
10/02/2019 ∙ by Lakshya Jain, et al. ∙ 23 ∙ share

read it
AI-GAN: Attack-Inspired Generation of Adversarial Examples

Adversarial examples that can fool deep models are mainly crafted by add...
02/06/2020 ∙ by Tao Bai, et al. ∙ 21 ∙ share

read it
Convolutional Neural Nets: Foundations, Computations, and New Applications

We review mathematical foundations of convolutional neural nets (CNNs) w...
01/13/2021 ∙ by Shengli Jiang, et al. ∙ 21 ∙ share

read it
On Need for Topology Awareness of Generative Models

Manifold assumption in learning states that: the data lie approximately ...
09/07/2019 ∙ by Uyeong Jang, et al. ∙ 20 ∙ share

read it
Adversarial VC-dimension and Sample Complexity of Neural Networks

Adversarial attacks during the testing phase of neural networks pose a c...
12/18/2019 ∙ by Zetong Qi, et al. ∙ 18 ∙ share

read it
TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning

The successful application of deep learning to many visual recognition t...
12/19/2019 ∙ by Zhongjie Yu, et al. ∙ 17 ∙ share

read it
A New Basis for Sparse PCA

The statistical and computational performance of sparse principal compon...
07/01/2020 ∙ by Fan Chen, et al. ∙ 17 ∙ share

read it
Flow-based Generative Models for Learning Manifold to Manifold Mappings

Many measurements or observations in computer vision and machine learnin...
12/18/2020 ∙ by Xingjian Zhen, et al. ∙ 17 ∙ share

read it
Transferring Multiscale Map Styles Using Generative Adversarial Networks

The advancement of the Artificial Intelligence (AI) technologies makes i...
05/06/2019 ∙ by Yuhao Kang, et al. ∙ 16 ∙ share

read it
Stochastic Learning for Sparse Discrete Markov Random Fields with Controlled Gradient Approximation Error

We study the L_1-regularized maximum likelihood estimator/estimation (ML...
05/12/2020 ∙ by Sinong Geng, et al. ∙ 16 ∙ share

read it
Looking back to lower-level information in few-shot learning

Humans are capable of learning new concepts from small numbers of exampl...
05/27/2020 ∙ by Zhongjie Yu, et al. ∙ 16 ∙ share

read it
Model Extraction and Active Learning

Machine learning is being increasingly used by individuals, research ins...
11/05/2018 ∙ by Varun Chandrasekaran, et al. ∙ 14 ∙ share

read it
Inferring Signaling Pathways with Probabilistic Programming

Cells regulate themselves via dizzyingly complex biochemical processes c...
05/28/2020 ∙ by David Merrell, et al. ∙ 13 ∙ share

read it
Can Adversarial Weight Perturbations Inject Neural Backdoors?

Adversarial machine learning has exposed several security hazards of neu...
08/04/2020 ∙ by Siddhant Garg, et al. ∙ 13 ∙ share

read it
Functional Regularization for Representation Learning: A Unified Theoretical Perspective

Unsupervised and self-supervised learning approaches have become a cruci...
08/06/2020 ∙ by Siddhant Garg, et al. ∙ 13 ∙ share

read it
Learning to Prune: Speeding up Repeated Computations

It is common to encounter situations where one must solve a sequence of ...
04/26/2019 ∙ by Daniel Alabi, et al. ∙ 12 ∙ share

read it
Gradients as Features for Deep Representation Learning

We address the challenging problem of deep representation learning–the e...
04/12/2020 ∙ by Fangzhou Mu, et al. ∙ 10 ∙ share

read it
Pufferfish: Communication-efficient Models At No Extra Cost

To mitigate communication overheads in distributed model training, sever...
03/05/2021 ∙ by Hongyi Wang, et al. ∙ 10 ∙ share

read it
Forster Decomposition and Learning Halfspaces with Noise

A Forster transform is an operation that turns a distribution into one w...
07/12/2021 ∙ by Ilias Diakonikolas, et al. ∙ 10 ∙ share

read it
Gradual Network for Single Image De-raining

Most advances in single image de-raining meet a key challenge, which is ...
09/20/2019 ∙ by Zhe Huang, et al. ∙ 9 ∙ share

read it
Interpretable and Accurate Fine-grained Recognition via Region Grouping

We present an interpretable deep model for fine-grained visual recogniti...
05/21/2020 ∙ by Zixuan Huang, et al. ∙ 8 ∙ share

read it
BlurNet: Defense by Filtering the Feature Maps

Recently, the field of adversarial machine learning has been garnering a...
08/06/2019 ∙ by Ravi Raju, et al. ∙ 7 ∙ share

read it
Nearly Tight Bounds for Robust Proper Learning of Halfspaces with a Margin

We study the problem of properly learning large margin halfspaces in th...
08/29/2019 ∙ by Ilias Diakonikolas, et al. ∙ 7 ∙ share

read it
High Flux Passive Imaging with Single-Photon Sensors

Single-photon avalanche diodes (SPADs) are an emerging technology with a...
02/26/2019 ∙ by Atul Ingle, et al. ∙ 6 ∙ share

read it
Semi Supervised Phrase Localization in a Bidirectional Caption-Image Retrieval Framework

We introduce a novel deep neural network architecture that links visual ...
08/08/2019 ∙ by Deepan Das, et al. ∙ 5 ∙ share

read it
Adversarially Robust Learning Could Leverage Computational Hardness

Over recent years, devising classification algorithms that are robust to...
05/28/2019 ∙ by Sanjam Garg, et al. ∙ 4 ∙ share

read it
Differential Scene Flow from Light Field Gradients

This paper presents novel techniques for recovering 3D dense scene flow,...
07/26/2019 ∙ by Sizhuo Ma, et al. ∙ 4 ∙ share

read it
Robust Mean Estimation under Coordinate-level Corruption

Data corruption, systematic or adversarial, may skew statistical estimat...
02/10/2020 ∙ by Zifan Liu, et al. ∙ 4 ∙ share

read it
Joint Reasoning for Temporal and Causal Relations

Understanding temporal and causal relations between events is a fundamen...
06/12/2019 ∙ by Qiang Ning, et al. ∙ 3 ∙ share

read it
Conservative Exploration using Interleaving

In many practical problems, a learning agent may want to learn the best ...
06/03/2018 ∙ by Sumeet Katariya, et al. ∙ 2 ∙ share

read it
A Shuffling Framework for Local Differential Privacy

ldp deployments are vulnerable to inference attacks as an adversary can ...
06/11/2021 ∙ by Casey Meehan, et al. ∙ 2 ∙ share

read it
Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models

Directed graphical models (DGMs) are a class of probabilistic models tha...
05/30/2019 ∙ by Amrita Roy Chowdhury, et al. ∙ 1 ∙ share

read it
The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise

We study the computational complexity of adversarially robust proper lea...
07/30/2020 ∙ by Ilias Diakonikolas, et al. ∙ 1 ∙ share

read it
The Optimality of Polynomial Regression for Agnostic Learning under Gaussian Marginals

We study the problem of agnostic learning under the Gaussian distributio...
02/08/2021 ∙ by Ilias Diakonikolas, et al. ∙ 1 ∙ share

read it
Practical Black-Box Attacks against Machine Learning

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vul...
02/08/2016 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it
Neural Signatures for Licence Plate Re-identification

The problem of vehicle licence plate re-identification is generally cons...
12/01/2017 ∙ by Abhinav Kumar, et al. ∙ 0 ∙ share

read it
Finding Differentially Covarying Needles in a Temporally Evolving Haystack: A Scan Statistics Perspective

Recent results in coupled or temporal graphical models offer schemes for...
11/20/2017 ∙ by Ronak Mehta, et al. ∙ 0 ∙ share

read it
Online Learning for Changing Environments using Coin Betting

A key challenge in online learning is that classical algorithms can be s...
11/06/2017 ∙ by Kwang-Sung Jun, et al. ∙ 0 ∙ share

read it
Analysis of Approximate Stochastic Gradient Using Quadratic Constraints and Sequential Semidefinite Programs

We present convergence rate analysis for the approximate stochastic grad...
11/03/2017 ∙ by Bin Hu, et al. ∙ 0 ∙ share

read it
Calibrated Boosting-Forest

Excellent ranking power along with well calibrated probability estimates...
10/16/2017 ∙ by Haozhen Wu, et al. ∙ 0 ∙ share

read it
Heat Kernel Smoothing in Irregular Image Domains

We present the discrete version of heat kernel smoothing on graph data s...
10/21/2017 ∙ by Moo K. Chung, et al. ∙ 0 ∙ share

read it
The Unintended Consequences of Overfitting: Training Data Inference Attacks

Machine learning algorithms that are applied to sensitive data pose a di...
09/05/2017 ∙ by Samuel Yeom, et al. ∙ 0 ∙ share

read it
A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees

We present a new Frank-Wolfe (FW) type algorithm that is applicable to m...
08/22/2017 ∙ by Sathya N. Ravi, et al. ∙ 0 ∙ share

read it
Neural Attribute Machines for Program Generation

Recurrent neural networks have achieved remarkable success at generating...
05/25/2017 ∙ by Matthew Amodio, et al. ∙ 0 ∙ share

read it
The Limitations of Deep Learning in Adversarial Settings

Deep learning takes advantage of large datasets and computationally effi...
11/24/2015 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks

Deep learning algorithms have been shown to perform extremely well on ma...
11/14/2015 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it

University of Wisconsin-Madison

Featured Researchers