Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

275481108 · Jun 202019922001200920172026
48 results for MI attacks

New attacks show data augmentation may not improve privacy.

problem Measuring privacy risk in models trained with data augmentation.
method Formulated membership inference as a set classification problem, designed input permutation invariant features.
result Proposed approach universally outperforms original methods on models trained with data augmentation.

Study quantized models' privacy against membership inference attacks.

problem Privacy risk in quantized machine learning models.
method Proposed a new MIS indicator for post-training quantization procedures, minimizing empirical loss.
result Demonstrated effectiveness of new MIS indicator in assessing and ranking privacy risk.

This paper quantifies how hard it is to identify specific data points in machine learning models.

problem Quantifying the difficulty of identifying specific data points in machine learning models.
method Characterizing optimal attacks and privacy defences, deriving impacts of noise and misspecification, and proposing a new covariance attack.
result The Mahalanobis distance explains the hardness of fixed-target membership inference attacks.

New method attacks GNNs with limited node access, increasing misclassification rate.

problem Attacking GNNs with limited node access and limited attack nodes.
method Generalized gradient-based attacks using importance scores derived from random walks.
result Proposed greedy procedure significantly increases misclassification rate.

It has been widely recognized that adversarial examples can be easily crafted to fool deep networks, which mainly root from the locally non-linear behavior nearby input examples. Applying mixup in training provides an effective mechanism to improve generalization performance and model robustness against adversarial per…

2019-09-25abs ↗pdf ↗

There are two major paradigms of white-box adversarial attacks that attempt to impose input perturbations. The first paradigm, called the fix-perturbation attack, crafts adversarial samples within a given perturbation level. The second paradigm, called the zero-confidence attack, finds the smallest perturbation needed …

2019-10-01abs ↗pdf ↗

Proposes MIGE for accurate MI gradient estimation in high-dimensional settings.

problem Intractability of MI in continuous and high-dimensional settings.
method Score estimation of implicit distributions for gradient estimation of MI.
result MIGE provides tight and smooth gradient estimation of MI in high-dimensional settings.

Study introduces a benchmark suite for evaluating neural MI estimators on real-world unstructured datasets.

problem Lack of comprehensive evaluation methods for neural MI estimators on real-world unstructured datasets.
method Developed a benchmark suite using same-class sampling and a binary symmetric channel trick.
result Showed accurate manipulation of true MI values of real-world datasets.

New methods estimate point-wise dependency from neural MI models.

problem Estimating point-wise dependency between different events.
method Developed two methods: Probabilistic Classifier and Density-Ratio Fitting.
result Demonstrated effectiveness in MI estimation, self-supervised representation learning, and cross-modal retrieval.

Bayesian nonparametric framework improves robustness of MI estimation.

problem Challenges in exact MI computation in high dimensions with intractable likelihoods.
method Uses a Dirichlet process posterior to regularize MI loss, reducing sensitivity to fluctuations and outliers.
result Significant improvements in convergence over EDF-based methods, enhancing robustness and accuracy.

This paper improves DNN generalization by accurately estimating mutual information.

problem Intractability of estimating mutual information in DNNs.
method Introduces a probabilistic representation of DNNs to accurately estimate mutual information.
result Derives a tighter generalization bound than previous relaxations.

Unified derivation of PAC-Bayes and MI bounds for general VC classes with fast rates.

problem Generalization bounds for machine learning models with VC classes.
method Unified derivation of conditional PAC-Bayesian and mutual information bounds, including MAC-Bayesian bounds.
result Nontrivial bounds for general VC classes and faster rates for specific conditions.

Paper refines InfoNCE for accurate mutual information estimation.

problem Indirect connection of InfoNCE to mutual information estimation.
method Introduces InfoNCE-anchor with an auxiliary anchor class for consistent density ratio estimation.
result InfoNCE-anchor yields a plug-in MI estimator with significantly reduced bias.

LMI approximates mutual information in high dimensions using learned low-dimensional representations.

problem Estimating mutual information between high-dimensional variables is challenging due to sample size limitations.
method Developed a method called latent MI (LMI) approximation that applies a nonparametric MI estimator to low-dimensional representations learned by a simple model architecture.
result LMI can approximate MI well for variables with >10^3 dimensions if their dependence structure has low intrinsic dimensionality.

Greedy MI maximization method outperforms existing approaches in nonlinear models.

problem Maximizing mutual information in nonlinear models with non-Gaussian noise.
method Greedy approaches based on log-Sobolev inequalities for computationally inexpensive MI lower bounds.
result Proposed method outperforms random selection and Gaussian approximations.

The market impact (MI) of Volume Weighted Average Price (VWAP) orders is a convex function of a trading rate, but most empirical estimates of transaction cost are concave functions. How is this possible? We show that isochronic (constant trading time) MI is slightly convex, and isochoric (constant trading volume) MI is…

2013-12-11abs ↗pdf ↗

InfoNCE objective is equivalent to ELBO in RPM, linking to self-supervised learning.

problem Improving self-supervised learning methods by connecting them to variational inference.
method Recognizing RPM and showing InfoNCE as a simplified lower bound on MI, equal to ELBO in infinite sample limit.
result The actual InfoNCE objective is equal to the ELBO (up to a constant) in the infinite sample limit.

A diversified portfolio is created by solving the MIS problem in large market graphs, outperforming conventional methods.

problem Finding the maximum independent set (MIS) in large-scale market graphs is computationally challenging.
method Solved the MIS problem using a quantum-inspired algorithm (Simulated Bifurcation) and a combinatorial optimization solver.
result The SB-based solver optimized MIS portfolios, achieving a Sharpe ratio of 1.16 and outperforming major indices.

Domain generation algorithms (DGAs) are commonly leveraged by malware to create lists of domain names which can be used for command and control (C&C) purposes. Approaches based on machine learning have recently been developed to automatically detect generated domain names in real-time. In this work, we present a novel …

2019-05-03abs ↗pdf ↗

Improves industry classification for diversified companies.

problem Traditional industry classification struggles with multi-sector conglomerates.
method Bayesian Non-Parametrics, Markov Updating, and hierarchical modeling.
result MIS-2 provides a measurable improvement over GICS in predicting future correlations.

InfoAtlas speeds up MI estimation for real-time data analysis.

problem Efficiently measuring statistical dependency between high-dimensional datasets.
method Directly infers mutual information in a single forward pass using a pretrained model.
result Matches state-of-the-art accuracy with 100x speedup.

Identity-link IRT improves TVD-MI scores without curvature violations.

problem Preserving additivity in TVD-MI scores for efficient LLM evaluation.
method Derives clipped-linear model from Gini entropy maximization, using identity link.
result Identity-link yields lower curvature violations (median curl 0.080-0.150) compared to probit/logit.

This paper improves MI-based BCIs by applying transfer learning across all components.

problem Reducing calibration effort for new subjects in MI-based BCIs.
method Proposes TL in spatial filtering, feature engineering, and classification blocks, and adds data alignment.
result Integrating data alignment and sophisticated TL significantly improves classification performance and reduces calibration effort.

While Multiple Instance (MI) data are point patterns -- sets or multi-sets of unordered points -- appropriate statistical point pattern models have not been used in MI learning. This article proposes a framework for model-based MI learning using point process theory. Likelihood functions for point pattern data derived …

2017-03-07abs ↗pdf ↗

TMLE improves causal effect estimation in missing data scenarios with various positivity violations.

problem Estimating causal effects in studies with missing data and positivity violations.
method Targeted Maximum Likelihood Estimation (TMLE) with various missing data methods.
result Complete cases with TMLE incorporating an outcome-missingness model exhibit lower bias and greater robustness against positivity violations.

This research improves EEG-based MI-BCI systems to be more resilient to emotional arousal.

problem Lack of robustness in EEG-based MI-BCI systems due to emotional arousal.
method Subjects were exposed to VR environments to induce high and low arousal states. Machine learning models were trained on proxy subjects instead of arousal states. MI models were trained for each subject.
result MI-BCI systems are made more resilient to emotional perturbations.

New bounds derived using conditional ff-information for machine learning models.

problem Improving generalization bounds in machine learning.
method Introducing novel information-theoretic generalization bounds via conditional ff-information.
result Derives generalization bounds applicable to both bounded and unbounded loss functions.

The study proposes a framework to assess sustainability of firms using fund-level classifications and portfolio holdings.

problem To capture market-based sustainability assessments of firms.
method Exploiting fund-level sustainability classifications and granular portfolio holdings to construct Market-Implied Sustainability (MIS) scores.
result MIS scores capture sustainability dimensions different from conventional ESG ratings and improve portfolio performance.

Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data. This comes with several immediate problems: For example, MI is notoriously hard to estimate, and using it as an objective…

2019-07-31abs ↗pdf ↗