
DPInstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations
Data poisoning and backdoor attacks manipulate training data to induce s...
read it

Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Nonuniform Attacks
Adversarial Training is proved to be an efficient method to defend again...
read it

VulnerabilityAware Poisoning Mechanism for Online RL with Unknown Dynamics
Poisoning attacks, although have been studied extensively in supervised ...
read it

Adaptive Learning Rates with Maximum Variation Averaging
Adaptive gradient methods such as RMSProp and Adam use exponential movin...
read it

Using Wavelets and Spectral Methods to Study Patterns in ImageClassification Datasets
Deep learning models extract, before a final classification layer, featu...
read it

Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers
Convex relaxations are effective for training and certifying neural netw...
read it

Convolutional TensorTrain LSTM for Spatiotemporal Learning
Higherorder Recurrent Neural Networks (RNNs) are effective for longter...
read it

TempLe: Learning Template of Transitions for Sample Efficient Multitask RL
Transferring knowledge among various environments is important to effici...
read it

Understanding Generalization in Deep Learning via Tensor Methods
Deep neural networks generalize well on unseen data though the number of...
read it

Can Agents Learn by Analogy? An Inferable Model for PAC Reinforcement Learning
Modelbased reinforcement learning algorithms make decisions by building...
read it

SamplingFree Learning of Bayesian Quantized Neural Networks
Bayesian learning of model parameters in neural networks is important in...
read it

Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?
Adversarial training is one of the strongest defenses against adversaria...
read it

Understanding Generalization through Visualizations
The power of neural networks lies in their ability to generalize to unse...
read it

SysML: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
read it

Tensorized Spectrum Preserving Compression for Neural Networks
Modern neural networks can have tens of millions of parameters, and are ...
read it

Guaranteed Simultaneous Asymmetric Tensor Decomposition via Orthogonalized Alternating Least Squares
We consider the asymmetric orthogonal tensor decomposition problem, and ...
read it

An endtoend Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm
Latent Dirichlet Allocation (LDA) is a powerful probabilistic model used...
read it

Unsupervised Learning of WordSequence Representations from Scratch via Convolutional Tensor Decomposition
Unsupervised text embeddings extraction is crucial for text understandin...
read it

Discovering Neuronal Cell Types and Their Gene Expression Profiles Using a Spatial Point Process Mixture Model
Cataloging the neuronal cell types that comprise circuitry of individual...
read it

Convolutional Dictionary Learning through Tensor Factorization
Tensor methods have emerged as a powerful paradigm for consistent learni...
read it

Escaping From Saddle Points  Online Stochastic Gradient for Tensor Decomposition
We analyze stochastic gradient descent for optimizing nonconvex functio...
read it

Online Tensor Methods for Learning Latent Variable Models
We introduce an online tensor decomposition based approach for two laten...
read it

Highdimensional structure estimation in Ising models: Local separation criterion
We consider the problem of highdimensional Ising (graphical) model sele...
read it
Furong Huang
is this you? claim profile