arXiv research

In this paper, we propose $\ell_p$-norm regularized models to seek near-optimal sparse portfolios. These sparse solutions reduce the complexity of portfolio implementation and management. Theoretical results are established to guarantee the sparsity of the second-order KKT points of the $\ell_p$-norm regularized models…

A new PCA method using T$\ell_1$-norm outperforms existing methods.

This paper tackles robustness of ensemble stumps and trees under general ℓ_p norm perturbations.

The paper proposes a new method for dictionary learning using $\ell_p$-norm maximization.

We give improved algorithms for the $\ell_{p}$-regression problem, $\min_{x} \|x\|_{p}$ such that $A x=b,$ for all $p \in (1,2) \cup (2,\infty).$ Our algorithms obtain a high accuracy solution in $\tilde{O}_{p}(m^{\frac{|p-2|}{2p + |p-2|}}) \le \tilde{O}_{p}(m^{\frac{1}{3}})$ iterations, where each iteration requires s…

The paper proposes a novel MKL approach for OCC using $\ell_p$-norm constraints.

Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. While current verification methods mainly focus on the $\ell_p$-norm threat model of the input instances, robustness verification against semantic adversarial attacks inducing large $\ell_p$-norm perturbations,…

ScoreAG generates unrestricted adversarial images maintaining semantic integrity.

Improved estimation of concentration using half-spaces for adversarial vulnerability.

Adversarial examples are malicious inputs crafted to cause a model to misclassify them. Their most common instantiation, "perturbation-based" adversarial examples introduce changes to the input that leave its true label unchanged, yet result in a different model prediction. Conversely, "invariance-based" adversarial ex…

We propose practical algorithms for entrywise $\ell_p$-norm low-rank approximation, for $p = 1$ or $p = \infty$. The proposed framework, which is non-convex and gradient-based, is easy to implement and typically attains better approximations, faster, than state of the art. From a theoretical standpoint, we show that th…

This work provides efficient algorithms for approximating ℓ_p sensitivities and related statistics.

Analyzes the complexity of linear hypothesis sets using Rademacher complexity.

New algorithm samples matrix rows proportional to their ℓ_p norm in a turnstile data stream.

In this paper, we discuss how a suitable family of tensor kernels can be used to efficiently solve nonparametric extensions of $\ell^p$ regularized learning methods. Our main contribution is proposing a fast dual algorithm, and showing that it allows to solve the problem efficiently. Our results contrast recent finding…

Active sampling algorithm for linear regression with various norms and improved query complexity.

Paper improves regret bounds for distributed experts problem.

New framework for private convex optimization in arbitrary norms.

This paper investigates the problem of sparse signal recovery in the presence of additive impulsive noise. The heavytailed impulsive noise is well modelled with stable distributions. Since there is no explicit formulation for the probability density function of $SαS$ distribution, alternative approximations like Genera…

New method optimizes offline linear bandits using different confidence sets.

This work presents a general framework for solving the low rank and/or sparse matrix minimization problems, which may involve multiple non-smooth terms. The Iteratively Reweighted Least Squares (IRLS) method is a fast solver, which smooths the objective function and minimizes it by alternately updating the variables an…

A novel one-class classifier fusion method for robust anomaly detection.

Deep neural networks perform well on real world data but are prone to adversarial perturbations: small changes in the input easily lead to misclassification. In this work, we propose an attack methodology not only for cases where the perturbations are measured by $\ell_p$ norms, but in fact any adversarial dissimilarit…

We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks. Specifically, we prove that $\ell_p$-norm constrained projected gradient ascent based adversarial training with an $\ell_q$-norm loss on the logits of clean and perturbed inputs is equivalent to data-…

New method approximates complex kernel norms with random features, making learning tractable.

Develops an ℓ_p theory for PCA and spectral clustering.

One-pass algorithm finds small subset for $\ell_p$ subspace approximation with additive error.

Recent research has shown that performance in signal processing tasks can often be significantly improved by using signal models based on sparse representations, where a signal is approximated using a small number of elements from a fixed dictionary. Unfortunately, inference in this model involves solving non-smooth op…

We present a general regularization-based framework for Multi-task learning (MTL), in which the similarity between tasks can be learned or refined using $\ell_p$-norm Multiple Kernel learning (MKL). Based on this very general formulation (including a general loss function), we derive the corresponding dual formulation …

New method accelerates steepest descent for convex optimization.

Learning linear combinations of multiple kernels is an appealing strategy when the right choice of features is unknown. Previous approaches to multiple kernel learning (MKL) promote sparse kernel combinations to support interpretability and scalability. Unfortunately, this 1-norm MKL is rarely observed to outperform tr…

Proposes an efficient method for sparse index tracking with $\ell_0$-norm constraints.

Novel framework improves randomized smoothing for various norms.

This paper assesses Gaussian and Exponential mechanisms for certifying adversarial robustness.

We derive an upper bound on the local Rademacher complexity of $\ell_p$-norm multiple kernel learning, which yields a tighter excess risk bound than global approaches. Previous local approaches aimed at analyzed the case $p=1$ only while our analysis covers all cases $1\leq p\leq\infty$, assuming the different feature …

A new algorithm solves the metric nearness problem efficiently.

Study improves image classifier robustness to random p-norm corruptions.

Study analyzes adversarial training dynamics without data distribution assumptions.

Unified algorithm for any $p$-norm experimental design problems.

Noise affects the effectiveness of interpolating models, especially those with strong inductive biases.

This project improves model robustness to affine transformations.

We propose a novel method for computing exact pointwise robustness of deep neural networks for all convex $\ell_p$ norms. Our algorithm, GeoCert, finds the largest $\ell_p$ ball centered at an input point $x_0$, within which the output class of a given neural network with ReLU nonlinearities remains unchanged. We relat…

In this paper, we study global existence and blow up properties to $L^p$ norm preserving non-local heat flows. We first study two kinds of $L^p$ norm preserving non-local flows and prove that these flows have the global solutions. Finally, we give a example to show that one kind of this heat flow may blow up in $L^{\in…

Generative models improve adversarial robustness by adding synthetic data.

We study \emph{TV regularization}, a widely used technique for eliciting structured sparsity. In particular, we propose efficient algorithms for computing prox-operators for $\ell_p$-norm TV. The most important among these is $\ell_1$-norm TV, for whose prox-operator we present a new geometric analysis which unveils a …

New robust loss functions improve matrix completion accuracy.

Random deep neural networks are robust to adversarial examples, scaling with input size and dimension.

Proposes a new regression method using $L_p$-norms for non-Gaussian noise.