Search Results for author:
Found 13 papers, 0 papers with code
Outlier Detection Using Generative Models with Theoretical Performance Guarantees
We propose an outlier detection approach for reconstructing the ground-truth signals modeled by generative models under sparse outliers.
Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems
We first argue that the MSE minimization approach is equivalent to a conditional entropy learning problem, and then propose a mutual information learning formulation for solving regression problems by using a reparameterization technique.
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained classifiers on benchmark datasets which can be used as backbone feature extractors in downstream tasks.
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
Deep learning systems have been reported to achieve state-of-the-art performances in many applications, and a key is the existence of well trained classifiers on benchmark datasets.
Solving Large Scale Quadratic Constrained Basis Pursuit
Inspired by alternating direction method of multipliers and the idea of operator splitting, we propose a efficient algorithm for solving large-scale quadratically constrained basis pursuit.
Optimal Pooling Matrix Design for Group Testing with Dilution (Row Degree) Constraints
In this paper, we consider the problem of designing optimal pooling matrix for group testing (for example, for COVID-19 virus testing) with the constraint that no more than $r>0$ samples can be pooled together, which we call "dilution constraint".
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning
We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by the mutual information between the degraded signal and the label of interest.
Do Deep Minds Think Alike? Selective Adversarial Attacks for Fine-Grained Manipulation of Multiple Deep Neural Networks
Recent works have demonstrated the existence of {\it adversarial examples} targeting a single machine learning system.
Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks
In this paper, we present a simple hypothesis about a feature compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully accounts for the observed fragility of AI classifiers to small adversarial perturbations.
An Information-Theoretic Explanation for the Adversarial Fragility of AI Classifiers
We present a simple hypothesis about a compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully accounts for the observed fragility of AI classifiers to small adversarial perturbations.
Outlier Detection using Generative Models with Theoretical Performance Guarantees
In this paper, we propose a generative model neural network approach for reconstructing the ground truth signals under sparse outliers.
Necessary and Sufficient Null Space Condition for Nuclear Norm Minimization in Low-Rank Matrix Recovery
In [12, 14, 15], the authors established the necessary and sufficient null space conditions for nuclear norm minimization to recover every possible low-rank matrix with rank at most r (the strong null space condition).
Separation-Free Super-Resolution from Compressed Measurements is Possible: an Orthonormal Atomic Norm Minimization Approach
However, it is known that in order for TV minimization and atomic norm minimization to recover the missing data or the frequencies, the underlying $R$ frequencies are required to be well-separated, even when the measurements are noiseless.
