arXiv research

New method improves neural network robustness without sacrificing generalization.

RILA learns HQMMs robustly against adversarial corruption.

Study on measuring vulnerability of neural network parameters via corruption.

In this paper, we consider batch supervised learning where an adversary is allowed to corrupt instances with arbitrarily large noise. The adversary is allowed to corrupt any $l$ features in each instance and the adversary can change their values in any way. This noise is introduced on test instances and the algorithm r…

Robust Q-learning algorithm resists corrupted rewards.

New algorithm resists corruption in linear contextual bandits.

New algorithm resists contamination in high-dimensional regression with optimal performance.

In high dimensions, most machine learning methods are brittle to even a small fraction of structured outliers. To address this, we introduce a new meta-algorithm that can take in a base learner such as least squares or stochastic gradient descent, and harden the learner to be resistant to outliers. Our method, Sever, p…

This paper approximates $p$-resistance for multi-class graph clustering.

New study shows acceleration in hyperbolic spaces is impossible for strongly geodesically convex functions.

FAL improves formation resistivity prediction from cased boreholes with noise resistance.

Robust algorithm for distributed optimization resistant to Byzantine failures.

Optimal trading strategy under market resistance and concave price impact model.

Extends Newton's minimal resistance problem to Riemannian surfaces.

New curvature defined via graph resistances leads to Ricci flow.

Identifying meaningful signal buried in noise is a problem of interest arising in diverse scenarios of data-driven modeling. We present here a theoretical framework for exploiting intrinsic geometry in data that resists noise corruption, and might be identifiable under severe obfuscation. Our approach is based on uncov…

New method calculates discrete curvature using effective resistances.

Extends Newton's minimal resistance problem to Lorentz-Minkowski space.

Paper defends diffusion models from membership inference attacks using Langevin dynamics.

Proposes a new method to improve deep model security against adversarial deformations.

The article deals with intrinsic metrics, Dirac operators and spectral triples induced by regular Dirichlet and resistance forms. We show, in particular, that if a local resistance form is given and the space is compact in resistance metric, then the intrinsic metric yields a geodesic space. Given a regular Dirichlet f…

Linear classifiers can resist adversarial attacks on Gaussian data.

Study predicts antimicrobial resistance in ICU patients quickly.

Graph curvature measured by inverse resistance distance.

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

Post-quantum cryptography needed for blockchain security.

Antimicrobial resistance is an important public health concern that has implications in the practice of medicine worldwide. Accurately predicting resistance phenotypes from genome sequences shows great promise in promoting better use of antimicrobial agents, by determining which antibiotics are likely to be effective i…

The paper studies minimal resistance dynamics in radial fields, finding unique solutions for incompressible flows.

Study optimal times to buy and sell stocks using support/resistance lines.

New method designs antimicrobial peptides with high potency and low toxicity.

Paper proves minimal resistance for a body in a fluid with decreasing density.

Motivation: HIV is difficult to treat because its virus mutates at a high rate and mutated viruses easily develop resistance to existing drugs. If the relationships between mutations and drug resistances can be determined from historical data, patients can be provided personalized treatment according to their own mutat…

This paper optimizes predicting support and resistance levels in financial markets.

Rapid identification of bacteria is essential to prevent the spread of infectious disease, help combat antimicrobial resistance, and improve patient outcomes. Raman optical spectroscopy promises to combine bacterial detection, identification, and antibiotic susceptibility testing in a single step. However, achieving cl…

Develops a comprehensive theory of corruption in supervised learning.

The paper discovers and evaluates support and resistance levels in financial time series.

New approach uses RS levels to improve stock trading RL model efficiency and stability.

Shells resist three out of six possible loads if simply connected.

New framework robustifies loss functions with quantiles for outlier resistance.

New algorithm robust to label corruptions in active learning.

Lithography simulation is one of the key steps in physical verification, enabled by the substantial optical and resist models. A resist model bridges the aerial image simulation to printed patterns. While the effectiveness of learning-based solutions for resist modeling has been demonstrated, they are considerably data…

Study finds corruption negatively impacts firm performance.

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

Unified framework for corruption-robust linear bandits with optimal gap-dependent misspecification bounds.

RESIST improves decentralized learning resilience against MITM attacks.

We report quantitative relations between corruption level and economic factors, such as country wealth and foreign investment per capita, which are characterized by a power law spanning multiple scales of wealth and investments per capita. These relations hold for diverse countries, and also remain stable over differen…

CUTS removes corruption from models without clean data, improving utility and security.

Study robust estimation under varying corruption probabilities in data.