arXiv research

New methods estimate causal effects through mediators, handling confounding without strict assumptions.

Semi-supervised learning is pervasive in real-world applications, where only a few labeled data are available and large amounts of instances remain unlabeled. Since AUC is an important model evaluation metric in classification, directly optimizing AUC in semi-supervised learning scenario has drawn much attention in the…

We study relations between special elliptic isometries in the complex hyperbolic plane. Relations of lengths 2, 3, and 4 are fully classified. Some relative SU(2,1)-character varieties of the quadruply punctured sphere are described and applied to the study of length 5 relations.

The paper connects knot homology, quantum 6j-symbols, and complements of knots.

We conjecture the existence of four independent gradings in the colored HOMFLY homology. We describe these gradings explicitly for the rectangular colored homology of torus knots and make qualitative predictions of various interesting structures and symmetries in the colored homology of general knots. We also give a si…

Scalable Gaussian process models trained with unbiased stochastic ELBO.

Semi-supervised ordinal regression (S$^2$OR) problems are ubiquitous in real-world applications, where only a few ordered instances are labeled and massive instances remain unlabeled. Recent researches have shown that directly optimizing concordance index or AUC can impose a better ranking on the data than optimizing t…

Here are described the axiumbilic points that appear in generic one parameter families of surfaces immersed in R4. At these points the ellipse of curvature of the immersion, Little, Garcia - Sotomayor has equal axes. A review is made on the basic preliminaries on axial curvature lines and the associated axiumbilic poin…

Boosts barely robust learners to be more adversarially robust.

AAT separates robust and non-robust features without supervision.

Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corruptions called adversarial examples. The adversarial examples study has recently become very popular and it sometimes even reduces the term "adv…

New research shows flat minima in robust loss landscapes correlate with good adversarial robustness.

Voting ensemble of robust models improves robustness.

Study privacy and robustness in learning halfspaces, proving hard trade-offs.

We introduce a new metric to evaluate corruption robustness of ML classifiers.

Robust learning method combines kernel smoothing and robust optimization.

Study shows how bias in optimization affects robustness in adversarial settings.

ClusTR improves clustering-based models' robustness without adversarial training.

SCORE resolves the robustness vs accuracy trade-off by redefining robust error.

Develops robust learning framework under distributional perturbations.

The study examines robust decision-making in volatile financial markets, finding action robustness is more impactful than uncertainty tolerance.

Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that restrict their practical applications. The adversarially robust training only makes the…

Proposes a new method for nonlinear models with robustness guarantees.

This work introduces new ways to compare adversarial robustness of classifiers globally.

Batch normalization shifts models to rely more on non-robust features.

Paper develops a robust Bayesian optimization method for noisy zeroth-order settings.

Paper proposes robust generative models using VAEs.

Paper proposes a robust metric learning algorithm.

HYDRA prunes robust neural networks to improve both benign and adversarial robustness.

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

The paper assesses machine learning robustness with covariate perturbations.

Study enhances robustness of In-CVaR based regression models under perturbation and contamination.

New mechanisms from primate vision improve neural network robustness.

Proposes robust model through Wasserstein geodesic interpolation of training data.

Proposes RFQI for robust RL using offline data.

This paper provides a comprehensive benchmark and taxonomy for certifiably robust DNN defenses.

This work improves certifiably robust models by distilling knowledge from adversarially robust teachers.

Paper reviews robustness in machine learning models and discusses training and certification methods.

RATIO improves neural network robustness and explainability.

Paper explores robust regression methods and their bias-variance trade-off.

Proposes a framework for defining robustness in neural networks.

New method makes CNN interpretations robust to adversarial attacks.

Given the apparent difficulty of learning models that are robust to adversarial perturbations, we propose tackling the simpler problem of developing adversarially robust features. Specifically, given a dataset and metric of interest, the goal is to return a function (or multiple functions) that 1) is robust to adversar…

This paper investigates how network width and depth affect adversarially robust DNNs.

Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally …

Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly conservative. Our soft-robust framework is an attempt to overcome this issue. In this pa…

This paper explores the trade-off between spatial and adversarial robustness in neural networks.

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on incorporating robustness into a state-of-the-art continuous control RL algorithm call…